[{"publication":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition","citation":{"apa":"Iofinova, E. B., Peste, E.-A., & Alistarh, D.-A. (2023). Bias in pruned vision models: In-depth analysis and countermeasures. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 24364–24373). Vancouver, BC, Canada: IEEE. https://doi.org/10.1109/cvpr52729.2023.02334","ieee":"E. B. Iofinova, E.-A. Peste, and D.-A. Alistarh, “Bias in pruned vision models: In-depth analysis and countermeasures,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 2023, pp. 24364–24373.","ista":"Iofinova EB, Peste E-A, Alistarh D-A. 2023. Bias in pruned vision models: In-depth analysis and countermeasures. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 24364–24373.","ama":"Iofinova EB, Peste E-A, Alistarh D-A. Bias in pruned vision models: In-depth analysis and countermeasures. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE; 2023:24364-24373. doi:10.1109/cvpr52729.2023.02334","chicago":"Iofinova, Eugenia B, Elena-Alexandra Peste, and Dan-Adrian Alistarh. “Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures.” In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 24364–73. IEEE, 2023. https://doi.org/10.1109/cvpr52729.2023.02334.","short":"E.B. Iofinova, E.-A. Peste, D.-A. Alistarh, in:, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2023, pp. 24364–24373.","mla":"Iofinova, Eugenia B., et al. “Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures.” 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2023, pp. 24364–73, doi:10.1109/cvpr52729.2023.02334."},"page":"24364-24373","date_published":"2023-08-22T00:00:00Z","day":"22","article_processing_charge":"No","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"14771","status":"public","title":"Bias in pruned vision models: In-depth analysis and countermeasures","oa_version":"Preprint","type":"conference","abstract":[{"text":"Pruning—that is, setting a significant subset of the parameters of a neural network to zero—is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate bias in the output of the compressed model. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood. In this work, we systematically investigate and characterize this phenomenon in Convolutional Neural Networks for computer vision. First, we show that it is in fact possible to obtain highly-sparse models, e.g. with less than 10% remaining weights, which do not decrease in accuracy nor substantially increase in bias when compared to dense models. At the same time, we also find that, at higher sparsities, pruned models exhibit higher uncertainty in their outputs, as well as increased correlations, which we directly link to increased bias. We propose easy-to-use criteria which, based only on the uncompressed model, establish whether bias will increase with pruning, and identify the samples most susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias.","lang":"eng"}],"external_id":{"isi":["001062531308068"],"arxiv":["2304.12622"]},"oa":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2304.12622","open_access":"1"}],"quality_controlled":"1","isi":1,"project":[{"_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A","grant_number":" W1260-N35","name":"Vienna Graduate School on Computational Optimization"},{"name":"Elastic Coordination for Scalable Machine Learning","call_identifier":"H2020","_id":"268A44D6-B435-11E9-9278-68D0E5697425","grant_number":"805223"}],"conference":{"start_date":"2023-06-17","location":"Vancouver, BC, Canada","end_date":"2023-06-24","name":"CVPR: Conference on Computer Vision and Pattern Recognition"},"doi":"10.1109/cvpr52729.2023.02334","language":[{"iso":"eng"}],"month":"08","publication_identifier":{"eisbn":["9798350301298"],"eissn":["2575-7075"]},"year":"2023","acknowledgement":"The authors would like to sincerely thank Sara Hooker for her feedback during the development of this work. EI was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35. AP and DA acknowledge generous ERC support, via Starting Grant 805223 ScaleML.","publication_status":"published","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"publisher":"IEEE","author":[{"full_name":"Iofinova, Eugenia B","first_name":"Eugenia B","last_name":"Iofinova","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","orcid":"0000-0002-7778-3221"},{"id":"32D78294-F248-11E8-B48F-1D18A9856A87","last_name":"Peste","first_name":"Elena-Alexandra","full_name":"Peste, Elena-Alexandra"},{"full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","last_name":"Alistarh"}],"related_material":{"link":[{"relation":"software","url":"https://github.com/IST-DASLab/pruned-vision-model-bias"}]},"date_created":"2024-01-10T08:42:40Z","date_updated":"2024-01-10T08:59:26Z","ec_funded":1},{"day":"15","month":"12","article_processing_charge":"No","language":[{"iso":"eng"}],"conference":{"name":"NeurIPS: Neural Information Processing Systems","location":"New Orleans, LA, United States","start_date":"2023-12-10","end_date":"2023-12-16"},"date_published":"2023-12-15T00:00:00Z","quality_controlled":"1","project":[{"_id":"059876FA-7A3F-11EA-A408-12923DDC885E","name":"Prix Lopez-Loretta 2019 - Marco Mondelli"}],"publication":"37th Annual Conference on Neural Information Processing Systems","citation":{"ama":"Súkeník P, Mondelli M, Lampert C. Deep neural collapse is provably optimal for the deep unconstrained features model. In: 37th Annual Conference on Neural Information Processing Systems.","ieee":"P. Súkeník, M. Mondelli, and C. Lampert, “Deep neural collapse is provably optimal for the deep unconstrained features model,” in 37th Annual Conference on Neural Information Processing Systems, New Orleans, LA, United States.","apa":"Súkeník, P., Mondelli, M., & Lampert, C. (n.d.). Deep neural collapse is provably optimal for the deep unconstrained features model. In 37th Annual Conference on Neural Information Processing Systems. New Orleans, LA, United States.","ista":"Súkeník P, Mondelli M, Lampert C. Deep neural collapse is provably optimal for the deep unconstrained features model. 37th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, NeurIPS, .","short":"P. Súkeník, M. Mondelli, C. Lampert, in:, 37th Annual Conference on Neural Information Processing Systems, n.d.","mla":"Súkeník, Peter, et al. “Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model.” 37th Annual Conference on Neural Information Processing Systems.","chicago":"Súkeník, Peter, Marco Mondelli, and Christoph Lampert. “Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model.” In 37th Annual Conference on Neural Information Processing Systems, n.d."},"oa":1,"main_file_link":[{"url":" https://doi.org/10.48550/arXiv.2305.13165","open_access":"1"}],"external_id":{"arxiv":["2305.13165"]},"abstract":[{"lang":"eng","text":"Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of NC to earlier layers of neural networks. However, while the NC in the last layer is well studied theoretically, much less is known about its multi-layered counterpart - deep neural collapse (DNC). In particular, existing work focuses either on linear layers or only on the last two layers at the price of an extra assumption. Our paper fills this gap by generalizing the established analytical framework for NC - the unconstrained features model - to multiple non-linear layers. Our key technical contribution is to show that, in a deep unconstrained features model, the unique global optimum for binary classification exhibits all the properties typical of DNC. This explains the existing experimental evidence of DNC. We also empirically show that (i) by optimizing deep unconstrained features models via gradient descent, the resulting solution agrees well with our theory, and (ii) trained networks recover the unconstrained features suitable for the occurrence of DNC, thus supporting the validity of this modeling principle."}],"alternative_title":["NeurIPS"],"type":"conference","date_updated":"2024-02-06T07:53:26Z","date_created":"2024-02-02T11:17:41Z","oa_version":"Preprint","author":[{"first_name":"Peter","last_name":"Súkeník","id":"d64d6a8d-eb8e-11eb-b029-96fd216dec3c","full_name":"Súkeník, Peter"},{"full_name":"Mondelli, Marco","first_name":"Marco","last_name":"Mondelli","id":"27EB676C-8706-11E9-9510-7717E6697425","orcid":"0000-0002-3242-7020"},{"last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"}],"status":"public","publication_status":"inpress","title":"Deep neural collapse is provably optimal for the deep unconstrained features model","department":[{"_id":"MaMo"},{"_id":"ChLa"}],"acknowledgement":"M. M. is partially supported by the 2019 Lopez-Loreta Prize. The authors would like to thank Eugenia Iofinova, Bernd Prach and Simone Bombari for valuable feedback on the manuscript.","_id":"14921","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","year":"2023"},{"day":"10","month":"11","article_processing_charge":"No","doi":"10.48550/ARXIV.2311.06103","date_published":"2023-11-10T00:00:00Z","language":[{"iso":"eng"}],"publication":"arXiv","citation":{"ama":"Prach B, Lampert C. 1-Lipschitz neural networks are more expressive with N-activations. arXiv. doi:10.48550/ARXIV.2311.06103","apa":"Prach, B., & Lampert, C. (n.d.). 1-Lipschitz neural networks are more expressive with N-activations. arXiv. https://doi.org/10.48550/ARXIV.2311.06103","ieee":"B. Prach and C. Lampert, “1-Lipschitz neural networks are more expressive with N-activations,” arXiv. .","ista":"Prach B, Lampert C. 1-Lipschitz neural networks are more expressive with N-activations. arXiv, 2311.06103.","short":"B. Prach, C. Lampert, ArXiv (n.d.).","mla":"Prach, Bernd, and Christoph Lampert. “1-Lipschitz Neural Networks Are More Expressive with N-Activations.” ArXiv, 2311.06103, doi:10.48550/ARXIV.2311.06103.","chicago":"Prach, Bernd, and Christoph Lampert. “1-Lipschitz Neural Networks Are More Expressive with N-Activations.” ArXiv, n.d. https://doi.org/10.48550/ARXIV.2311.06103."},"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2311.06103"}],"external_id":{"arxiv":["2311.06103"]},"oa":1,"abstract":[{"lang":"eng","text":"A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs. Mathematically, this means one strives for networks with a small Lipschitz constant. Several recent works have focused on how to construct such Lipschitz networks, typically by imposing constraints on the weight matrices. In this work, we study an orthogonal aspect, namely the role of the activation function. We show that commonly used activation functions, such as MaxMin, as well as all piece-wise linear ones with two segments unnecessarily restrict the class of representable functions, even in the simplest one-dimensional setting. We furthermore introduce the new N-activation function that is provably more expressive than currently popular activation functions. We provide code at this https URL."}],"article_number":"2311.06103","type":"preprint","author":[{"full_name":"Prach, Bernd","first_name":"Bernd","last_name":"Prach","id":"2D561D42-C427-11E9-89B4-9C1AE6697425"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"date_created":"2024-02-28T17:59:32Z","date_updated":"2024-03-04T07:02:39Z","oa_version":"Preprint","_id":"15039","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","year":"2023","publication_status":"submitted","status":"public","title":"1-Lipschitz neural networks are more expressive with N-activations","department":[{"_id":"GradSch"},{"_id":"ChLa"}]},{"author":[{"full_name":"Scott, Jonathan A","id":"e499926b-f6e0-11ea-865d-9c63db0031e8","first_name":"Jonathan A","last_name":"Scott"},{"last_name":"Yeo","first_name":"Michelle X","id":"2D82B818-F248-11E8-B48F-1D18A9856A87","full_name":"Yeo, Michelle X"},{"full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"date_created":"2023-02-20T08:21:50Z","date_updated":"2023-02-21T08:20:18Z","file":[{"creator":"chl","content_type":"application/pdf","file_size":291893,"file_name":"2210.06434.pdf","access_level":"open_access","date_created":"2023-02-20T08:21:35Z","date_updated":"2023-02-20T08:21:35Z","success":1,"checksum":"7ab20543fd4393f14fb857ce2e4f03c6","file_id":"12661","relation":"main_file"}],"oa_version":"Preprint","year":"2022","_id":"12660","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"Cross-client Label Propagation for transductive federated learning","status":"public","publication_status":"submitted","ddc":["004"],"department":[{"_id":"ChLa"}],"abstract":[{"text":"We present Cross-Client Label Propagation(XCLP), a new method for transductive federated learning. XCLP estimates a data graph jointly from the data of multiple clients and computes labels for the unlabeled data by propagating label information across the graph. To avoid clients having to share their data with anyone, XCLP employs two cryptographically secure protocols: secure Hamming distance computation and secure summation. We demonstrate two distinct applications of XCLP within federated learning. In the first, we use it in a one-shot way to predict labels for unseen test points. In the second, we use it to repeatedly pseudo-label unlabeled training data in a federated semi-supervised setting. Experiments on both real federated and standard benchmark datasets show that in both applications XCLP achieves higher classification accuracy than alternative approaches.","lang":"eng"}],"file_date_updated":"2023-02-20T08:21:35Z","license":"https://creativecommons.org/licenses/by/4.0/","article_number":"2210.06434","type":"preprint","date_published":"2022-10-12T00:00:00Z","doi":"10.48550/arXiv.2210.06434","language":[{"iso":"eng"}],"publication":"arXiv","citation":{"chicago":"Scott, Jonathan A, Michelle X Yeo, and Christoph Lampert. “Cross-Client Label Propagation for Transductive Federated Learning.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2210.06434.","mla":"Scott, Jonathan A., et al. “Cross-Client Label Propagation for Transductive Federated Learning.” ArXiv, 2210.06434, doi:10.48550/arXiv.2210.06434.","short":"J.A. Scott, M.X. Yeo, C. Lampert, ArXiv (n.d.).","ista":"Scott JA, Yeo MX, Lampert C. Cross-client Label Propagation for transductive federated learning. arXiv, 2210.06434.","apa":"Scott, J. A., Yeo, M. X., & Lampert, C. (n.d.). Cross-client Label Propagation for transductive federated learning. arXiv. https://doi.org/10.48550/arXiv.2210.06434","ieee":"J. A. Scott, M. X. Yeo, and C. Lampert, “Cross-client Label Propagation for transductive federated learning,” arXiv. .","ama":"Scott JA, Yeo MX, Lampert C. Cross-client Label Propagation for transductive federated learning. arXiv. doi:10.48550/arXiv.2210.06434"},"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"external_id":{"arxiv":["2210.06434"]},"oa":1,"month":"10","day":"12","has_accepted_license":"1","article_processing_charge":"No"},{"month":"08","day":"29","article_processing_charge":"No","has_accepted_license":"1","publication":"arXiv","citation":{"chicago":"Súkeník, Peter, and Christoph Lampert. “Generalization in Multi-Objective Machine Learning.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2208.13499.","mla":"Súkeník, Peter, and Christoph Lampert. “Generalization in Multi-Objective Machine Learning.” ArXiv, 2208.13499, doi:10.48550/arXiv.2208.13499.","short":"P. Súkeník, C. Lampert, ArXiv (n.d.).","ista":"Súkeník P, Lampert C. Generalization in Multi-objective machine learning. arXiv, 2208.13499.","apa":"Súkeník, P., & Lampert, C. (n.d.). Generalization in Multi-objective machine learning. arXiv. https://doi.org/10.48550/arXiv.2208.13499","ieee":"P. Súkeník and C. Lampert, “Generalization in Multi-objective machine learning,” arXiv. .","ama":"Súkeník P, Lampert C. Generalization in Multi-objective machine learning. arXiv. doi:10.48550/arXiv.2208.13499"},"external_id":{"arxiv":["2208.13499"]},"main_file_link":[{"url":" https://doi.org/10.48550/arXiv.2208.13499","open_access":"1"}],"oa":1,"language":[{"iso":"eng"}],"doi":"10.48550/arXiv.2208.13499","date_published":"2022-08-29T00:00:00Z","article_number":"2208.13499","type":"preprint","abstract":[{"lang":"eng","text":"Modern machine learning tasks often require considering not just one but multiple objectives. For example, besides the prediction quality, this could be the efficiency, robustness or fairness of the learned models, or any of their combinations. Multi-objective learning offers a natural framework for handling such problems without having to commit to early trade-offs. Surprisingly, statistical learning theory so far offers almost no insight into the generalization properties of multi-objective learning. In this work, we make first steps to fill this gap: we establish foundational generalization bounds for the multi-objective setting as well as generalization and excess bounds for learning with scalarizations. We also provide the first theoretical analysis of the relation between the Pareto-optimal sets of the true objectives and the Pareto-optimal sets of their empirical approximations from training data. In particular, we show a surprising asymmetry: all Pareto-optimal solutions can be approximated by empirically Pareto-optimal ones, but not vice versa."}],"status":"public","ddc":["004"],"publication_status":"submitted","title":"Generalization in Multi-objective machine learning","department":[{"_id":"ChLa"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"12662","year":"2022","date_created":"2023-02-20T08:23:06Z","date_updated":"2023-02-21T08:24:55Z","oa_version":"Preprint","author":[{"full_name":"Súkeník, Peter","id":"d64d6a8d-eb8e-11eb-b029-96fd216dec3c","last_name":"Súkeník","first_name":"Peter"},{"full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}]},{"status":"public","ddc":["000"],"title":"FLEA: Provably robust fair multisource learning from unreliable training data","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"12495","oa_version":"Published Version","file":[{"success":1,"checksum":"97c8a8470759cab597abb973ca137a3b","date_updated":"2023-02-23T10:30:04Z","date_created":"2023-02-23T10:30:04Z","file_id":"12673","relation":"main_file","creator":"dernst","content_type":"application/pdf","file_size":1948063,"access_level":"open_access","file_name":"2022_TMLR_Iofinova.pdf"}],"type":"journal_article","abstract":[{"text":"Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of\r\nmachine learning with far-reaching societal impact. However, existing fair learning methods\r\nare vulnerable to accidental or malicious artifacts in the training data, which can cause\r\nthem to unknowingly produce unfair classifiers. In this work we address the problem of\r\nfair learning from unreliable training data in the robust multisource setting, where the\r\navailable training data comes from multiple sources, a fraction of which might not be representative of the true data distribution. We introduce FLEA, a filtering-based algorithm\r\nthat identifies and suppresses those data sources that would have a negative impact on\r\nfairness or accuracy if they were used for training. As such, FLEA is not a replacement of\r\nprior fairness-aware learning methods but rather an augmentation that makes any of them\r\nrobust against unreliable training data. We show the effectiveness of our approach by a\r\ndiverse range of experiments on multiple datasets. Additionally, we prove formally that\r\n–given enough data– FLEA protects the learner against corruptions as long as the fraction of\r\naffected data sources is less than half. Our source code and documentation are available at\r\nhttps://github.com/ISTAustria-CVML/FLEA.","lang":"eng"}],"article_type":"original","citation":{"mla":"Iofinova, Eugenia B., et al. “FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data.” Transactions on Machine Learning Research, ML Research Press, 2022.","short":"E.B. Iofinova, N.H. Konstantinov, C. Lampert, Transactions on Machine Learning Research (2022).","chicago":"Iofinova, Eugenia B, Nikola H Konstantinov, and Christoph Lampert. “FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data.” Transactions on Machine Learning Research. ML Research Press, 2022.","ama":"Iofinova EB, Konstantinov NH, Lampert C. FLEA: Provably robust fair multisource learning from unreliable training data. Transactions on Machine Learning Research. 2022.","ista":"Iofinova EB, Konstantinov NH, Lampert C. 2022. FLEA: Provably robust fair multisource learning from unreliable training data. Transactions on Machine Learning Research.","apa":"Iofinova, E. B., Konstantinov, N. H., & Lampert, C. (2022). FLEA: Provably robust fair multisource learning from unreliable training data. Transactions on Machine Learning Research. ML Research Press.","ieee":"E. B. Iofinova, N. H. Konstantinov, and C. Lampert, “FLEA: Provably robust fair multisource learning from unreliable training data,” Transactions on Machine Learning Research. ML Research Press, 2022."},"publication":"Transactions on Machine Learning Research","date_published":"2022-12-22T00:00:00Z","article_processing_charge":"No","has_accepted_license":"1","day":"22","publisher":"ML Research Press","department":[{"_id":"ChLa"}],"publication_status":"published","year":"2022","acknowledgement":"The authors would like to thank Bernd Prach, Elias Frantar, Alexandra Peste, Mahdi Nikdan, and Peter Súkeník for their helpful feedback. This research was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp). This publication was made possible by an ETH AI Center postdoctoral fellowship granted to Nikola Konstantinov. Eugenia Iofinova was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35. ","date_updated":"2023-02-23T10:30:54Z","date_created":"2023-02-02T20:29:57Z","related_material":{"link":[{"relation":"software","description":"source code","url":"https://github.com/ISTAustria-CVML/FLEA"}]},"author":[{"full_name":"Iofinova, Eugenia B","first_name":"Eugenia B","last_name":"Iofinova","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","orcid":"0000-0002-7778-3221"},{"full_name":"Konstantinov, Nikola H","first_name":"Nikola H","last_name":"Konstantinov","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87"},{"orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","full_name":"Lampert, Christoph"}],"file_date_updated":"2023-02-23T10:30:04Z","project":[{"name":"Vienna Graduate School on Computational Optimization","grant_number":" W1260-N35","_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A"}],"quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"main_file_link":[{"url":"https://openreview.net/forum?id=XsPopigZXV","open_access":"1"}],"external_id":{"arxiv":["2106.11732"]},"oa":1,"language":[{"iso":"eng"}],"acknowledged_ssus":[{"_id":"ScienComp"}],"publication_identifier":{"issn":["2835-8856"]},"month":"12"},{"page":"350-365","publication":"Computer Vision – ECCV 2022","citation":{"chicago":"Prach, Bernd, and Christoph Lampert. “Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks.” In Computer Vision – ECCV 2022, 13681:350–65. Springer Nature, 2022. https://doi.org/10.1007/978-3-031-19803-8_21.","mla":"Prach, Bernd, and Christoph Lampert. “Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks.” Computer Vision – ECCV 2022, vol. 13681, Springer Nature, 2022, pp. 350–65, doi:10.1007/978-3-031-19803-8_21.","short":"B. Prach, C. Lampert, in:, Computer Vision – ECCV 2022, Springer Nature, 2022, pp. 350–365.","ista":"Prach B, Lampert C. 2022. Almost-orthogonal layers for efficient general-purpose Lipschitz networks. Computer Vision – ECCV 2022. ECCV: European Conference on Computer Vision, LNCS, vol. 13681, 350–365.","ieee":"B. Prach and C. Lampert, “Almost-orthogonal layers for efficient general-purpose Lipschitz networks,” in Computer Vision – ECCV 2022, Tel Aviv, Israel, 2022, vol. 13681, pp. 350–365.","apa":"Prach, B., & Lampert, C. (2022). Almost-orthogonal layers for efficient general-purpose Lipschitz networks. In Computer Vision – ECCV 2022 (Vol. 13681, pp. 350–365). Tel Aviv, Israel: Springer Nature. https://doi.org/10.1007/978-3-031-19803-8_21","ama":"Prach B, Lampert C. Almost-orthogonal layers for efficient general-purpose Lipschitz networks. In: Computer Vision – ECCV 2022. Vol 13681. Springer Nature; 2022:350-365. doi:10.1007/978-3-031-19803-8_21"},"date_published":"2022-10-23T00:00:00Z","scopus_import":"1","day":"23","article_processing_charge":"No","title":"Almost-orthogonal layers for efficient general-purpose Lipschitz networks","status":"public","intvolume":" 13681","_id":"11839","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"Preprint","alternative_title":["LNCS"],"type":"conference","abstract":[{"lang":"eng","text":"It is a highly desirable property for deep networks to be robust against\r\nsmall input changes. One popular way to achieve this property is by designing\r\nnetworks with a small Lipschitz constant. In this work, we propose a new\r\ntechnique for constructing such Lipschitz networks that has a number of\r\ndesirable properties: it can be applied to any linear network layer\r\n(fully-connected or convolutional), it provides formal guarantees on the\r\nLipschitz constant, it is easy to implement and efficient to run, and it can be\r\ncombined with any training objective and optimization method. In fact, our\r\ntechnique is the first one in the literature that achieves all of these\r\nproperties simultaneously. Our main contribution is a rescaling-based weight\r\nmatrix parametrization that guarantees each network layer to have a Lipschitz\r\nconstant of at most 1 and results in the learned weight matrices to be close to\r\northogonal. Hence we call such layers almost-orthogonal Lipschitz (AOL).\r\nExperiments and ablation studies in the context of image classification with\r\ncertified robust accuracy confirm that AOL layers achieve results that are on\r\npar with most existing methods. Yet, they are simpler to implement and more\r\nbroadly applicable, because they do not require computationally expensive\r\nmatrix orthogonalization or inversion steps as part of the network\r\narchitecture. We provide code at https://github.com/berndprach/AOL."}],"quality_controlled":"1","main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.2208.03160"}],"external_id":{"arxiv":["2208.03160"]},"oa":1,"language":[{"iso":"eng"}],"conference":{"location":"Tel Aviv, Israel","start_date":"2022-10-23","end_date":"2022-10-27","name":"ECCV: European Conference on Computer Vision"},"doi":"10.1007/978-3-031-19803-8_21","month":"10","publication_identifier":{"isbn":["9783031198021"],"eisbn":["9783031198038"]},"publication_status":"published","department":[{"_id":"GradSch"},{"_id":"ChLa"}],"publisher":"Springer Nature","year":"2022","date_created":"2022-08-12T15:09:47Z","date_updated":"2023-05-03T08:00:46Z","volume":13681,"author":[{"id":"2D561D42-C427-11E9-89B4-9C1AE6697425","first_name":"Bernd","last_name":"Prach","full_name":"Prach, Bernd"},{"full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph"}]},{"author":[{"full_name":"Lampert, Jasmin","last_name":"Lampert","first_name":"Jasmin"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4561-241X"}],"oa_version":"None","date_updated":"2023-08-02T14:27:50Z","date_created":"2022-02-10T14:08:23Z","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","_id":"10752","year":"2022","department":[{"_id":"ChLa"}],"publisher":"IEEE","title":"Overcoming rare-language discrimination in multi-lingual sentiment analysis","status":"public","publication_status":"published","abstract":[{"text":"The digitalization of almost all aspects of our everyday lives has led to unprecedented amounts of data being freely available on the Internet. In particular social media platforms provide rich sources of user-generated data, though typically in unstructured form, and with high diversity, such as written in many different languages. Automatically identifying meaningful information in such big data resources and extracting it efficiently is one of the ongoing challenges of our time. A common step for this is sentiment analysis, which forms the foundation for tasks such as opinion mining or trend prediction. Unfortunately, publicly available tools for this task are almost exclusively available for English-language texts. Consequently, a large fraction of the Internet users, who do not communicate in English, are ignored in automatized studies, a phenomenon called rare-language discrimination.In this work we propose a technique to overcome this problem by a truly multi-lingual model, which can be trained automatically without linguistic knowledge or even the ability to read the many target languages. The main step is to combine self-annotation, specifically the use of emoticons as a proxy for labels, with multi-lingual sentence representations.To evaluate our method we curated several large datasets from data obtained via the free Twitter streaming API. The results show that our proposed multi-lingual training is able to achieve sentiment predictions at the same quality level for rare languages as for frequent ones, and in particular clearly better than what mono-lingual training achieves on the same data. ","lang":"eng"}],"type":"conference","date_published":"2022-01-13T00:00:00Z","doi":"10.1109/bigdata52589.2021.9672003","conference":{"name":"Big Data: International Conference on Big Data","location":"Orlando, FL, United States","start_date":"2021-12-15","end_date":"2021-12-18"},"language":[{"iso":"eng"}],"external_id":{"isi":["000800559505036"]},"citation":{"ista":"Lampert J, Lampert C. 2022. Overcoming rare-language discrimination in multi-lingual sentiment analysis. 2021 IEEE International Conference on Big Data. Big Data: International Conference on Big Data, 5185–5192.","apa":"Lampert, J., & Lampert, C. (2022). Overcoming rare-language discrimination in multi-lingual sentiment analysis. In 2021 IEEE International Conference on Big Data (pp. 5185–5192). Orlando, FL, United States: IEEE. https://doi.org/10.1109/bigdata52589.2021.9672003","ieee":"J. Lampert and C. Lampert, “Overcoming rare-language discrimination in multi-lingual sentiment analysis,” in 2021 IEEE International Conference on Big Data, Orlando, FL, United States, 2022, pp. 5185–5192.","ama":"Lampert J, Lampert C. Overcoming rare-language discrimination in multi-lingual sentiment analysis. In: 2021 IEEE International Conference on Big Data. IEEE; 2022:5185-5192. doi:10.1109/bigdata52589.2021.9672003","chicago":"Lampert, Jasmin, and Christoph Lampert. “Overcoming Rare-Language Discrimination in Multi-Lingual Sentiment Analysis.” In 2021 IEEE International Conference on Big Data, 5185–92. IEEE, 2022. https://doi.org/10.1109/bigdata52589.2021.9672003.","mla":"Lampert, Jasmin, and Christoph Lampert. “Overcoming Rare-Language Discrimination in Multi-Lingual Sentiment Analysis.” 2021 IEEE International Conference on Big Data, IEEE, 2022, pp. 5185–92, doi:10.1109/bigdata52589.2021.9672003.","short":"J. Lampert, C. Lampert, in:, 2021 IEEE International Conference on Big Data, IEEE, 2022, pp. 5185–5192."},"publication":"2021 IEEE International Conference on Big Data","page":"5185-5192","isi":1,"quality_controlled":"1","article_processing_charge":"No","publication_identifier":{"isbn":["9781665439022"]},"month":"01","day":"13"},{"publication_identifier":{"eisbn":["9781665490627"],"eissn":["2831-7475"]},"month":"11","oa":1,"external_id":{"arxiv":["2206.05181"],"isi":["000897707602018"]},"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2206.05181"}],"quality_controlled":"1","isi":1,"doi":"10.1109/icpr56361.2022.9956195","conference":{"end_date":"2022-08-25","start_date":"2022-08-21","location":"Montreal, Canada","name":"ICPR: International Conference on Pattern Recognition"},"language":[{"iso":"eng"}],"year":"2022","department":[{"_id":"ChLa"}],"publisher":"Institute of Electrical and Electronics Engineers","publication_status":"published","author":[{"full_name":"Tomaszewska, Paulina","first_name":"Paulina","last_name":"Tomaszewska"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"volume":2022,"date_created":"2023-01-12T12:09:38Z","date_updated":"2023-08-04T09:06:34Z","scopus_import":"1","article_processing_charge":"No","day":"29","citation":{"ama":"Tomaszewska P, Lampert C. Lightweight conditional model extrapolation for streaming data under class-prior shift. In: 26th International Conference on Pattern Recognition. Vol 2022. Institute of Electrical and Electronics Engineers; 2022:2128-2134. doi:10.1109/icpr56361.2022.9956195","ista":"Tomaszewska P, Lampert C. 2022. Lightweight conditional model extrapolation for streaming data under class-prior shift. 26th International Conference on Pattern Recognition. ICPR: International Conference on Pattern Recognition vol. 2022, 2128–2134.","apa":"Tomaszewska, P., & Lampert, C. (2022). Lightweight conditional model extrapolation for streaming data under class-prior shift. In 26th International Conference on Pattern Recognition (Vol. 2022, pp. 2128–2134). Montreal, Canada: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/icpr56361.2022.9956195","ieee":"P. Tomaszewska and C. Lampert, “Lightweight conditional model extrapolation for streaming data under class-prior shift,” in 26th International Conference on Pattern Recognition, Montreal, Canada, 2022, vol. 2022, pp. 2128–2134.","mla":"Tomaszewska, Paulina, and Christoph Lampert. “Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift.” 26th International Conference on Pattern Recognition, vol. 2022, Institute of Electrical and Electronics Engineers, 2022, pp. 2128–34, doi:10.1109/icpr56361.2022.9956195.","short":"P. Tomaszewska, C. Lampert, in:, 26th International Conference on Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 2128–2134.","chicago":"Tomaszewska, Paulina, and Christoph Lampert. “Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift.” In 26th International Conference on Pattern Recognition, 2022:2128–34. Institute of Electrical and Electronics Engineers, 2022. https://doi.org/10.1109/icpr56361.2022.9956195."},"publication":"26th International Conference on Pattern Recognition","page":"2128-2134","date_published":"2022-11-29T00:00:00Z","type":"conference","abstract":[{"lang":"eng","text":"We introduce LIMES, a new method for learning with non-stationary streaming data, inspired by the recent success of meta-learning. The main idea is not to attempt to learn a single classifier that would have to work well across all occurring data distributions, nor many separate classifiers, but to exploit a hybrid strategy: we learn a single set of model parameters from which a specific classifier for any specific data distribution is derived via classifier adaptation. Assuming a multiclass classification setting with class-prior shift, the adaptation step can be performed analytically with only the classifier’s bias terms being affected. Another contribution of our work is an extrapolation step that predicts suitable adaptation parameters for future time steps based on the previous data. In combination, we obtain a lightweight procedure for learning from streaming data with varying class distribution that adds no trainable parameters and almost no memory or computational overhead compared to training a single model. Experiments on a set of exemplary tasks using Twitter data show that LIMES achieves higher accuracy than alternative approaches, especially with respect to the relevant real-world metric of lowest within-day accuracy."}],"_id":"12161","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","intvolume":" 2022","status":"public","title":"Lightweight conditional model extrapolation for streaming data under class-prior shift","oa_version":"Preprint"},{"date_created":"2023-01-16T10:06:00Z","date_updated":"2023-08-04T10:33:28Z","author":[{"full_name":"Iofinova, Eugenia B","first_name":"Eugenia B","last_name":"Iofinova","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","orcid":"0000-0002-7778-3221"},{"full_name":"Peste, Elena-Alexandra","id":"32D78294-F248-11E8-B48F-1D18A9856A87","last_name":"Peste","first_name":"Elena-Alexandra"},{"full_name":"Kurtz, Mark","first_name":"Mark","last_name":"Kurtz"},{"first_name":"Dan-Adrian","last_name":"Alistarh","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0003-3650-940X","full_name":"Alistarh, Dan-Adrian"}],"related_material":{"record":[{"relation":"dissertation_contains","status":"public","id":"13074"}]},"publication_status":"published","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"publisher":"Institute of Electrical and Electronics Engineers","year":"2022","acknowledgement":"he authors would like to sincerely thank Christoph Lampert and Nir Shavit for fruitful discussions during the development of this work, and Eldar Kurtic for experimental support. EI was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35, while AP and DA acknowledge generous support by the ERC, via Starting Grant 805223 ScaleML.","ec_funded":1,"language":[{"iso":"eng"}],"conference":{"name":"CVPR: Computer Vision and Pattern Recognition","end_date":"2022-06-24","location":"New Orleans, LA, United States","start_date":"2022-06-18"},"doi":"10.1109/cvpr52688.2022.01195","quality_controlled":"1","isi":1,"project":[{"name":"Vienna Graduate School on Computational Optimization","grant_number":" W1260-N35","_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A"},{"_id":"268A44D6-B435-11E9-9278-68D0E5697425","grant_number":"805223","name":"Elastic Coordination for Scalable Machine Learning","call_identifier":"H2020"}],"oa":1,"external_id":{"isi":["000870759105034"],"arxiv":["2111.13445"]},"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2111.13445","open_access":"1"}],"month":"09","publication_identifier":{"eissn":["2575-7075"]},"oa_version":"Preprint","title":"How well do sparse ImageNet models transfer?","status":"public","_id":"12299","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","abstract":[{"lang":"eng","text":"Transfer learning is a classic paradigm by which models pretrained on large “upstream” datasets are adapted to yield good results on “downstream” specialized datasets. Generally, more accurate models on the “upstream” dataset tend to provide better transfer accuracy “downstream”. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned-that is, compressed by sparsifiying their connections. We consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, regrowth, lottery-ticket, and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods. The code is available at: https://github.com/IST-DASLab/sparse-imagenet-transfer."}],"type":"conference","date_published":"2022-09-27T00:00:00Z","page":"12256-12266","publication":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition","citation":{"ama":"Iofinova EB, Peste E-A, Kurtz M, Alistarh D-A. How well do sparse ImageNet models transfer? In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Institute of Electrical and Electronics Engineers; 2022:12256-12266. doi:10.1109/cvpr52688.2022.01195","ista":"Iofinova EB, Peste E-A, Kurtz M, Alistarh D-A. 2022. How well do sparse ImageNet models transfer? 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Computer Vision and Pattern Recognition, 12256–12266.","ieee":"E. B. Iofinova, E.-A. Peste, M. Kurtz, and D.-A. Alistarh, “How well do sparse ImageNet models transfer?,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, United States, 2022, pp. 12256–12266.","apa":"Iofinova, E. B., Peste, E.-A., Kurtz, M., & Alistarh, D.-A. (2022). How well do sparse ImageNet models transfer? In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 12256–12266). New Orleans, LA, United States: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/cvpr52688.2022.01195","mla":"Iofinova, Eugenia B., et al. “How Well Do Sparse ImageNet Models Transfer?” 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 12256–66, doi:10.1109/cvpr52688.2022.01195.","short":"E.B. Iofinova, E.-A. Peste, M. Kurtz, D.-A. Alistarh, in:, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 12256–12266.","chicago":"Iofinova, Eugenia B, Elena-Alexandra Peste, Mark Kurtz, and Dan-Adrian Alistarh. “How Well Do Sparse ImageNet Models Transfer?” In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12256–66. Institute of Electrical and Electronics Engineers, 2022. https://doi.org/10.1109/cvpr52688.2022.01195."},"day":"27","article_processing_charge":"No","scopus_import":"1"},{"keyword":["Fairness","robustness","data poisoning","trustworthy machine learning","PAC learning"],"scopus_import":"1","day":"01","article_processing_charge":"No","has_accepted_license":"1","article_type":"original","page":"1-60","publication":"Journal of Machine Learning Research","citation":{"chicago":"Konstantinov, Nikola H, and Christoph Lampert. “Fairness-Aware PAC Learning from Corrupted Data.” Journal of Machine Learning Research. ML Research Press, 2022.","mla":"Konstantinov, Nikola H., and Christoph Lampert. “Fairness-Aware PAC Learning from Corrupted Data.” Journal of Machine Learning Research, vol. 23, ML Research Press, 2022, pp. 1–60.","short":"N.H. Konstantinov, C. Lampert, Journal of Machine Learning Research 23 (2022) 1–60.","ista":"Konstantinov NH, Lampert C. 2022. Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. 23, 1–60.","apa":"Konstantinov, N. H., & Lampert, C. (2022). Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. ML Research Press.","ieee":"N. H. Konstantinov and C. Lampert, “Fairness-aware PAC learning from corrupted data,” Journal of Machine Learning Research, vol. 23. ML Research Press, pp. 1–60, 2022.","ama":"Konstantinov NH, Lampert C. Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. 2022;23:1-60."},"date_published":"2022-05-01T00:00:00Z","type":"journal_article","abstract":[{"text":"Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many approaches have been developed for training fair models from data, little is known about the robustness of these methods to data corruption. In this work we consider fairness-aware learning under worst-case data manipulations. We show that an adversary can in some situations force any learner to return an overly biased classifier, regardless of the sample size and with or without degrading\r\naccuracy, and that the strength of the excess bias increases for learning problems with underrepresented protected groups in the data. We also prove that our hardness results are tight up to constant factors. To this end, we study two natural learning algorithms that optimize for both accuracy and fairness and show that these algorithms enjoy guarantees that are order-optimal in terms of the corruption ratio and the protected groups frequencies in the large data\r\nlimit.","lang":"eng"}],"ddc":["004"],"status":"public","title":"Fairness-aware PAC learning from corrupted data","intvolume":" 23","_id":"10802","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"Published Version","file":[{"date_created":"2022-07-12T15:08:28Z","date_updated":"2022-07-12T15:08:28Z","checksum":"9cac897b54a0ddf3a553a2c33e88cfda","success":1,"relation":"main_file","file_id":"11570","file_size":551862,"content_type":"application/pdf","creator":"kschuh","file_name":"2022_JournalMachineLearningResearch_Konstantinov.pdf","access_level":"open_access"}],"month":"05","publication_identifier":{"issn":["1532-4435"],"eissn":["1533-7928"]},"quality_controlled":"1","external_id":{"arxiv":["2102.06004"]},"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"oa":1,"language":[{"iso":"eng"}],"file_date_updated":"2022-07-12T15:08:28Z","publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"ML Research Press","acknowledgement":"The authors thank Eugenia Iofinova and Bernd Prach for providing feedback on early versions of this paper. This publication was made possible by an ETH AI Center postdoctoral fellowship to Nikola Konstantinov.","year":"2022","date_created":"2022-02-28T14:05:42Z","date_updated":"2023-09-26T10:44:37Z","volume":23,"author":[{"first_name":"Nikola H","last_name":"Konstantinov","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87","full_name":"Konstantinov, Nikola H"},{"orcid":"0000-0002-4561-241X","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","full_name":"Lampert, Christoph"}],"related_material":{"record":[{"status":"public","relation":"dissertation_contains","id":"10799"},{"id":"13241","relation":"shorter_version","status":"public"}]}},{"date_published":"2022-12-01T00:00:00Z","citation":{"ama":"Konstantinov NH, Lampert C. On the impossibility of fairness-aware learning from corrupted data. In: Proceedings of Machine Learning Research. Vol 171. ML Research Press; 2022:59-83.","apa":"Konstantinov, N. H., & Lampert, C. (2022). On the impossibility of fairness-aware learning from corrupted data. In Proceedings of Machine Learning Research (Vol. 171, pp. 59–83). ML Research Press.","ieee":"N. H. Konstantinov and C. Lampert, “On the impossibility of fairness-aware learning from corrupted data,” in Proceedings of Machine Learning Research, 2022, vol. 171, pp. 59–83.","ista":"Konstantinov NH, Lampert C. 2022. On the impossibility of fairness-aware learning from corrupted data. Proceedings of Machine Learning Research. vol. 171, 59–83.","short":"N.H. Konstantinov, C. Lampert, in:, Proceedings of Machine Learning Research, ML Research Press, 2022, pp. 59–83.","mla":"Konstantinov, Nikola H., and Christoph Lampert. “On the Impossibility of Fairness-Aware Learning from Corrupted Data.” Proceedings of Machine Learning Research, vol. 171, ML Research Press, 2022, pp. 59–83.","chicago":"Konstantinov, Nikola H, and Christoph Lampert. “On the Impossibility of Fairness-Aware Learning from Corrupted Data.” In Proceedings of Machine Learning Research, 171:59–83. ML Research Press, 2022."},"publication":"Proceedings of Machine Learning Research","page":"59-83","article_processing_charge":"No","day":"01","scopus_import":"1","oa_version":"Preprint","_id":"13241","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","intvolume":" 171","status":"public","title":"On the impossibility of fairness-aware learning from corrupted data","abstract":[{"lang":"eng","text":"Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. Many approaches for training fair models from data have been developed and an implicit assumption about such algorithms is that they are able to recover a fair model, despite potential historical biases in the data. In this work we show a number of impossibility results that indicate that there is no learning algorithm that can recover a fair model when a proportion of the dataset is subject to arbitrary manipulations. Specifically, we prove that there are situations in which an adversary can force any learner to return a biased classifier, with or without degrading accuracy, and that the strength of this bias increases for learning problems with underrepresented protected groups in the data. Our results emphasize on the importance of studying further data corruption models of various strength and of establishing stricter data collection practices for fairness-aware learning."}],"type":"conference","language":[{"iso":"eng"}],"external_id":{"arxiv":["2102.06004"]},"oa":1,"main_file_link":[{"url":"https://arxiv.org/abs/2102.06004","open_access":"1"}],"quality_controlled":"1","publication_identifier":{"eissn":["2640-3498"]},"month":"12","related_material":{"record":[{"id":"10802","relation":"extended_version","status":"public"}]},"author":[{"full_name":"Konstantinov, Nikola H","first_name":"Nikola H","last_name":"Konstantinov","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph"}],"volume":171,"date_created":"2023-07-16T22:01:13Z","date_updated":"2023-09-26T10:44:37Z","year":"2022","acknowledgement":"This paper is a shortened, workshop version of Konstantinov and Lampert (2021),\r\nhttps://arxiv.org/abs/2102.06004. For further results, including an analysis of algorithms achieving the lower bounds from this paper, we refer to the full version.","publisher":"ML Research Press","department":[{"_id":"ChLa"}],"publication_status":"published"},{"file":[{"content_type":"application/pdf","file_size":4204905,"creator":"nkonstan","file_name":"thesis.pdf","access_level":"open_access","date_updated":"2022-03-06T11:42:54Z","date_created":"2022-03-06T11:42:54Z","checksum":"626bc523ae8822d20e635d0e2d95182e","success":1,"relation":"main_file","file_id":"10823"},{"relation":"source_file","file_id":"10824","checksum":"e2ca2b88350ac8ea1515b948885cbcb1","date_created":"2022-03-06T11:42:57Z","date_updated":"2022-03-10T12:11:48Z","access_level":"closed","file_name":"thesis.zip","file_size":22841103,"content_type":"application/x-zip-compressed","creator":"nkonstan"}],"oa_version":"Published Version","title":"Robustness and fairness in machine learning","ddc":["000"],"status":"public","_id":"10799","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","abstract":[{"text":"Because of the increasing popularity of machine learning methods, it is becoming important to understand the impact of learned components on automated decision-making systems and to guarantee that their consequences are beneficial to society. In other words, it is necessary to ensure that machine learning is sufficiently trustworthy to be used in real-world applications. This thesis studies two properties of machine learning models that are highly desirable for the\r\nsake of reliability: robustness and fairness. In the first part of the thesis we study the robustness of learning algorithms to training data corruption. Previous work has shown that machine learning models are vulnerable to a range\r\nof training set issues, varying from label noise through systematic biases to worst-case data manipulations. This is an especially relevant problem from a present perspective, since modern machine learning methods are particularly data hungry and therefore practitioners often have to rely on data collected from various external sources, e.g. from the Internet, from app users or via crowdsourcing. Naturally, such sources vary greatly in the quality and reliability of the\r\ndata they provide. With these considerations in mind, we study the problem of designing machine learning algorithms that are robust to corruptions in data coming from multiple sources. We show that, in contrast to the case of a single dataset with outliers, successful learning within this model is possible both theoretically and practically, even under worst-case data corruptions. The second part of this thesis deals with fairness-aware machine learning. There are multiple areas where machine learning models have shown promising results, but where careful considerations are required, in order to avoid discrimanative decisions taken by such learned components. Ensuring fairness can be particularly challenging, because real-world training datasets are expected to contain various forms of historical bias that may affect the learning process. In this thesis we show that data corruption can indeed render the problem of achieving fairness impossible, by tightly characterizing the theoretical limits of fair learning under worst-case data manipulations. However, assuming access to clean data, we also show how fairness-aware learning can be made practical in contexts beyond binary classification, in particular in the challenging learning to rank setting.","lang":"eng"}],"alternative_title":["ISTA Thesis"],"type":"dissertation","date_published":"2022-03-08T00:00:00Z","page":"176","citation":{"ista":"Konstantinov NH. 2022. Robustness and fairness in machine learning. Institute of Science and Technology Austria.","ieee":"N. H. Konstantinov, “Robustness and fairness in machine learning,” Institute of Science and Technology Austria, 2022.","apa":"Konstantinov, N. H. (2022). Robustness and fairness in machine learning. Institute of Science and Technology Austria. https://doi.org/10.15479/at:ista:10799","ama":"Konstantinov NH. Robustness and fairness in machine learning. 2022. doi:10.15479/at:ista:10799","chicago":"Konstantinov, Nikola H. “Robustness and Fairness in Machine Learning.” Institute of Science and Technology Austria, 2022. https://doi.org/10.15479/at:ista:10799.","mla":"Konstantinov, Nikola H. Robustness and Fairness in Machine Learning. Institute of Science and Technology Austria, 2022, doi:10.15479/at:ista:10799.","short":"N.H. Konstantinov, Robustness and Fairness in Machine Learning, Institute of Science and Technology Austria, 2022."},"day":"08","has_accepted_license":"1","article_processing_charge":"No","keyword":["robustness","fairness","machine learning","PAC learning","adversarial learning"],"date_created":"2022-02-28T13:03:49Z","date_updated":"2023-10-17T12:31:54Z","author":[{"first_name":"Nikola H","last_name":"Konstantinov","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87","full_name":"Konstantinov, Nikola H"}],"related_material":{"record":[{"id":"8724","relation":"part_of_dissertation","status":"public"},{"id":"10803","status":"public","relation":"part_of_dissertation"},{"id":"10802","relation":"part_of_dissertation","status":"public"},{"id":"6590","relation":"part_of_dissertation","status":"public"}]},"publication_status":"published","publisher":"Institute of Science and Technology Austria","department":[{"_id":"GradSch"},{"_id":"ChLa"}],"year":"2022","file_date_updated":"2022-03-10T12:11:48Z","ec_funded":1,"degree_awarded":"PhD","supervisor":[{"full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"language":[{"iso":"eng"}],"doi":"10.15479/at:ista:10799","project":[{"_id":"2564DBCA-B435-11E9-9278-68D0E5697425","grant_number":"665385","name":"International IST Doctoral Program","call_identifier":"H2020"}],"oa":1,"month":"03","publication_identifier":{"isbn":["978-3-99078-015-2"],"issn":["2663-337X"]}},{"scopus_import":"1","series_title":"LNCS","day":"17","article_processing_charge":"No","has_accepted_license":"1","publication":"42nd German Conference on Pattern Recognition","citation":{"ama":"Volhejn V, Lampert C. Does SGD implicitly optimize for smoothness? In: 42nd German Conference on Pattern Recognition. Vol 12544. LNCS. Springer; 2021:246-259. doi:10.1007/978-3-030-71278-5_18","apa":"Volhejn, V., & Lampert, C. (2021). Does SGD implicitly optimize for smoothness? In 42nd German Conference on Pattern Recognition (Vol. 12544, pp. 246–259). Tübingen, Germany: Springer. https://doi.org/10.1007/978-3-030-71278-5_18","ieee":"V. Volhejn and C. Lampert, “Does SGD implicitly optimize for smoothness?,” in 42nd German Conference on Pattern Recognition, Tübingen, Germany, 2021, vol. 12544, pp. 246–259.","ista":"Volhejn V, Lampert C. 2021. Does SGD implicitly optimize for smoothness? 42nd German Conference on Pattern Recognition. DAGM GCPR: German Conference on Pattern Recognition LNCS vol. 12544, 246–259.","short":"V. Volhejn, C. Lampert, in:, 42nd German Conference on Pattern Recognition, Springer, 2021, pp. 246–259.","mla":"Volhejn, Vaclav, and Christoph Lampert. “Does SGD Implicitly Optimize for Smoothness?” 42nd German Conference on Pattern Recognition, vol. 12544, Springer, 2021, pp. 246–59, doi:10.1007/978-3-030-71278-5_18.","chicago":"Volhejn, Vaclav, and Christoph Lampert. “Does SGD Implicitly Optimize for Smoothness?” In 42nd German Conference on Pattern Recognition, 12544:246–59. LNCS. Springer, 2021. https://doi.org/10.1007/978-3-030-71278-5_18."},"page":"246-259","date_published":"2021-03-17T00:00:00Z","type":"conference","abstract":[{"text":"Modern neural networks can easily fit their training set perfectly. Surprisingly, despite being “overfit” in this way, they tend to generalize well to future data, thereby defying the classic bias–variance trade-off of machine learning theory. Of the many possible explanations, a prevalent one is that training by stochastic gradient descent (SGD) imposes an implicit bias that leads it to learn simple functions, and these simple functions generalize well. However, the specifics of this implicit bias are not well understood.\r\nIn this work, we explore the smoothness conjecture which states that SGD is implicitly biased towards learning functions that are smooth. We propose several measures to formalize the intuitive notion of smoothness, and we conduct experiments to determine whether SGD indeed implicitly optimizes for these measures. Our findings rule out the possibility that smoothness measures based on first-order derivatives are being implicitly enforced. They are supportive, though, of the smoothness conjecture for measures based on second-order derivatives.","lang":"eng"}],"_id":"9210","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","ddc":["510"],"status":"public","title":"Does SGD implicitly optimize for smoothness?","intvolume":" 12544","file":[{"success":1,"checksum":"3e3628ab1cf658d82524963f808004ea","date_created":"2022-08-12T07:27:58Z","date_updated":"2022-08-12T07:27:58Z","file_id":"11820","relation":"main_file","creator":"dernst","file_size":420234,"content_type":"application/pdf","access_level":"open_access","file_name":"2020_GCPR_submitted_Volhejn.pdf"}],"oa_version":"Submitted Version","month":"03","publication_identifier":{"isbn":["9783030712778"],"eissn":["1611-3349"],"issn":["0302-9743"]},"oa":1,"quality_controlled":"1","conference":{"end_date":"2020-10-01","start_date":"2020-09-28","location":"Tübingen, Germany","name":"DAGM GCPR: German Conference on Pattern Recognition "},"doi":"10.1007/978-3-030-71278-5_18","language":[{"iso":"eng"}],"file_date_updated":"2022-08-12T07:27:58Z","year":"2021","publication_status":"published","publisher":"Springer","department":[{"_id":"ChLa"}],"author":[{"first_name":"Vaclav","last_name":"Volhejn","id":"d5235fb4-7a6d-11eb-b254-f25d12d631a8","full_name":"Volhejn, Vaclav"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"date_created":"2021-03-01T09:01:16Z","date_updated":"2022-08-12T07:28:47Z","volume":12544},{"abstract":[{"lang":"eng","text":"We study the inductive bias of two-layer ReLU networks trained by gradient flow. We identify a class of easy-to-learn (`orthogonally separable') datasets, and characterise the solution that ReLU networks trained on such datasets converge to. Irrespective of network width, the solution turns out to be a combination of two max-margin classifiers: one corresponding to the positive data subset and one corresponding to the negative data subset. The proof is based on the recently introduced concept of extremal sectors, for which we prove a number of properties in the context of orthogonal separability. In particular, we prove stationarity of activation patterns from some time onwards, which enables a reduction of the ReLU network to an ensemble of linear subnetworks."}],"file_date_updated":"2021-05-24T11:15:57Z","type":"conference","file":[{"checksum":"f34ff17017527db5ba6927f817bdd125","date_updated":"2021-05-24T11:15:57Z","date_created":"2021-05-24T11:15:57Z","relation":"main_file","file_id":"9417","file_size":502356,"content_type":"application/pdf","creator":"bphuong","access_level":"open_access","file_name":"iclr2021_conference.pdf"}],"oa_version":"Published Version","date_updated":"2023-09-07T13:29:50Z","date_created":"2021-05-24T11:16:46Z","related_material":{"record":[{"id":"9418","relation":"dissertation_contains","status":"public"}]},"author":[{"id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87","first_name":"Phuong","last_name":"Bui Thi Mai","full_name":"Bui Thi Mai, Phuong"},{"last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"}],"department":[{"_id":"GradSch"},{"_id":"ChLa"}],"title":"The inductive bias of ReLU networks on orthogonally separable data","publication_status":"published","status":"public","ddc":["000"],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"9416","year":"2021","has_accepted_license":"1","article_processing_charge":"No","month":"05","day":"01","scopus_import":"1","language":[{"iso":"eng"}],"date_published":"2021-05-01T00:00:00Z","conference":{"start_date":"2021-05-03","location":"Virtual","end_date":"2021-05-07","name":" ICLR: International Conference on Learning Representations"},"quality_controlled":"1","oa":1,"main_file_link":[{"open_access":"1","url":"https://openreview.net/pdf?id=krz7T0xU9Z_"}],"citation":{"short":"M. Phuong, C. Lampert, in:, 9th International Conference on Learning Representations, 2021.","mla":"Phuong, Mary, and Christoph Lampert. “The Inductive Bias of ReLU Networks on Orthogonally Separable Data.” 9th International Conference on Learning Representations, 2021.","chicago":"Phuong, Mary, and Christoph Lampert. “The Inductive Bias of ReLU Networks on Orthogonally Separable Data.” In 9th International Conference on Learning Representations, 2021.","ama":"Phuong M, Lampert C. The inductive bias of ReLU networks on orthogonally separable data. In: 9th International Conference on Learning Representations. ; 2021.","apa":"Phuong, M., & Lampert, C. (2021). The inductive bias of ReLU networks on orthogonally separable data. In 9th International Conference on Learning Representations. Virtual.","ieee":"M. Phuong and C. Lampert, “The inductive bias of ReLU networks on orthogonally separable data,” in 9th International Conference on Learning Representations, Virtual, 2021.","ista":"Phuong M, Lampert C. 2021. The inductive bias of ReLU networks on orthogonally separable data. 9th International Conference on Learning Representations. ICLR: International Conference on Learning Representations."},"publication":"9th International Conference on Learning Representations"},{"author":[{"full_name":"Konstantinov, Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87","first_name":"Nikola H","last_name":"Konstantinov"},{"first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4561-241X","full_name":"Lampert, Christoph"}],"related_material":{"record":[{"id":"10799","status":"public","relation":"dissertation_contains"}]},"date_created":"2022-02-28T14:13:59Z","date_updated":"2023-09-07T13:42:08Z","oa_version":"Preprint","_id":"10803","year":"2021","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"Fairness through regularization for learning to rank","status":"public","publication_status":"submitted","department":[{"_id":"ChLa"}],"abstract":[{"text":"Given the abundance of applications of ranking in recent years, addressing fairness concerns around automated ranking systems becomes necessary for increasing the trust among end-users. Previous work on fair ranking has mostly focused on application-specific fairness notions, often tailored to online advertising, and it rarely considers learning as part of the process. In this work, we show how to transfer numerous fairness notions from binary classification to a learning to rank setting. Our formalism allows us to design methods for incorporating fairness objectives with provable generalization guarantees. An extensive experimental evaluation shows that our method can improve ranking fairness substantially with no or only little loss of model quality.","lang":"eng"}],"article_number":"2102.05996","type":"preprint","doi":"10.48550/arXiv.2102.05996","date_published":"2021-06-07T00:00:00Z","language":[{"iso":"eng"}],"publication":"arXiv","main_file_link":[{"url":"https://arxiv.org/abs/2102.05996","open_access":"1"}],"citation":{"short":"N.H. Konstantinov, C. Lampert, ArXiv (n.d.).","mla":"Konstantinov, Nikola H., and Christoph Lampert. “Fairness through Regularization for Learning to Rank.” ArXiv, 2102.05996, doi:10.48550/arXiv.2102.05996.","chicago":"Konstantinov, Nikola H, and Christoph Lampert. “Fairness through Regularization for Learning to Rank.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2102.05996.","ama":"Konstantinov NH, Lampert C. Fairness through regularization for learning to rank. arXiv. doi:10.48550/arXiv.2102.05996","apa":"Konstantinov, N. H., & Lampert, C. (n.d.). Fairness through regularization for learning to rank. arXiv. https://doi.org/10.48550/arXiv.2102.05996","ieee":"N. H. Konstantinov and C. Lampert, “Fairness through regularization for learning to rank,” arXiv. .","ista":"Konstantinov NH, Lampert C. Fairness through regularization for learning to rank. arXiv, 2102.05996."},"oa":1,"external_id":{"arxiv":["2102.05996"]},"month":"06","day":"07","article_processing_charge":"No"},{"file":[{"content_type":"application/pdf","file_size":2673905,"creator":"bphuong","file_name":"mph-thesis-v519-pdfimages.pdf","access_level":"open_access","date_updated":"2021-05-24T11:22:29Z","date_created":"2021-05-24T11:22:29Z","checksum":"4f0abe64114cfed264f9d36e8d1197e3","success":1,"relation":"main_file","file_id":"9419"},{"file_size":92995100,"content_type":"application/zip","creator":"bphuong","file_name":"thesis.zip","access_level":"closed","date_updated":"2021-05-24T11:56:02Z","date_created":"2021-05-24T11:56:02Z","checksum":"f5699e876bc770a9b0df8345a77720a2","relation":"source_file","file_id":"9420"}],"oa_version":"Published Version","_id":"9418","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","status":"public","ddc":["000"],"title":"Underspecification in deep learning","abstract":[{"text":"Deep learning is best known for its empirical success across a wide range of applications\r\nspanning computer vision, natural language processing and speech. Of equal significance,\r\nthough perhaps less known, are its ramifications for learning theory: deep networks have\r\nbeen observed to perform surprisingly well in the high-capacity regime, aka the overfitting\r\nor underspecified regime. Classically, this regime on the far right of the bias-variance curve\r\nis associated with poor generalisation; however, recent experiments with deep networks\r\nchallenge this view.\r\n\r\nThis thesis is devoted to investigating various aspects of underspecification in deep learning.\r\nFirst, we argue that deep learning models are underspecified on two levels: a) any given\r\ntraining dataset can be fit by many different functions, and b) any given function can be\r\nexpressed by many different parameter configurations. We refer to the second kind of\r\nunderspecification as parameterisation redundancy and we precisely characterise its extent.\r\nSecond, we characterise the implicit criteria (the inductive bias) that guide learning in the\r\nunderspecified regime. Specifically, we consider a nonlinear but tractable classification\r\nsetting, and show that given the choice, neural networks learn classifiers with a large margin.\r\nThird, we consider learning scenarios where the inductive bias is not by itself sufficient to\r\ndeal with underspecification. We then study different ways of ‘tightening the specification’: i)\r\nIn the setting of representation learning with variational autoencoders, we propose a hand-\r\ncrafted regulariser based on mutual information. ii) In the setting of binary classification, we\r\nconsider soft-label (real-valued) supervision. We derive a generalisation bound for linear\r\nnetworks supervised in this way and verify that soft labels facilitate fast learning. Finally, we\r\nexplore an application of soft-label supervision to the training of multi-exit models.","lang":"eng"}],"type":"dissertation","alternative_title":["ISTA Thesis"],"date_published":"2021-05-30T00:00:00Z","citation":{"chicago":"Phuong, Mary. “Underspecification in Deep Learning.” Institute of Science and Technology Austria, 2021. https://doi.org/10.15479/AT:ISTA:9418.","short":"M. Phuong, Underspecification in Deep Learning, Institute of Science and Technology Austria, 2021.","mla":"Phuong, Mary. Underspecification in Deep Learning. Institute of Science and Technology Austria, 2021, doi:10.15479/AT:ISTA:9418.","apa":"Phuong, M. (2021). Underspecification in deep learning. Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:9418","ieee":"M. Phuong, “Underspecification in deep learning,” Institute of Science and Technology Austria, 2021.","ista":"Phuong M. 2021. Underspecification in deep learning. Institute of Science and Technology Austria.","ama":"Phuong M. Underspecification in deep learning. 2021. doi:10.15479/AT:ISTA:9418"},"page":"125","article_processing_charge":"No","has_accepted_license":"1","day":"30","related_material":{"record":[{"status":"deleted","relation":"part_of_dissertation","id":"7435"},{"id":"7481","relation":"part_of_dissertation","status":"public"},{"status":"public","relation":"part_of_dissertation","id":"9416"},{"relation":"part_of_dissertation","status":"public","id":"7479"}]},"author":[{"last_name":"Bui Thi Mai","first_name":"Phuong","id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87","full_name":"Bui Thi Mai, Phuong"}],"date_created":"2021-05-24T13:06:23Z","date_updated":"2023-09-08T11:11:12Z","year":"2021","department":[{"_id":"GradSch"},{"_id":"ChLa"}],"publisher":"Institute of Science and Technology Austria","publication_status":"published","file_date_updated":"2021-05-24T11:56:02Z","doi":"10.15479/AT:ISTA:9418","language":[{"iso":"eng"}],"acknowledged_ssus":[{"_id":"ScienComp"},{"_id":"CampIT"},{"_id":"E-Lib"}],"supervisor":[{"first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph"}],"degree_awarded":"PhD","oa":1,"publication_identifier":{"issn":["2663-337X"]},"month":"05"},{"author":[{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"edition":"2","date_updated":"2024-02-19T10:59:04Z","date_created":"2024-02-14T14:05:32Z","oa_version":"None","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"14987","year":"2021","publication_status":"published","status":"public","title":"Zero-Shot Learning","department":[{"_id":"ChLa"}],"editor":[{"first_name":"Katsushi","last_name":"Ikeuchi","full_name":"Ikeuchi, Katsushi"}],"publisher":"Springer","abstract":[{"lang":"eng","text":"The goal of zero-shot learning is to construct a classifier that can identify object classes for which no training examples are available. When training data for some of the object classes is available but not for others, the name generalized zero-shot learning is commonly used.\r\nIn a wider sense, the phrase zero-shot is also used to describe other machine learning-based approaches that require no training data from the problem of interest, such as zero-shot action recognition or zero-shot machine translation."}],"type":"book_chapter","place":"Cham","date_published":"2021-10-13T00:00:00Z","doi":"10.1007/978-3-030-63416-2_874","language":[{"iso":"eng"}],"publication":"Computer Vision","citation":{"chicago":"Lampert, Christoph. “Zero-Shot Learning.” In Computer Vision, edited by Katsushi Ikeuchi, 2nd ed., 1395–97. Cham: Springer, 2021. https://doi.org/10.1007/978-3-030-63416-2_874.","mla":"Lampert, Christoph. “Zero-Shot Learning.” Computer Vision, edited by Katsushi Ikeuchi, 2nd ed., Springer, 2021, pp. 1395–97, doi:10.1007/978-3-030-63416-2_874.","short":"C. Lampert, in:, K. Ikeuchi (Ed.), Computer Vision, 2nd ed., Springer, Cham, 2021, pp. 1395–1397.","ista":"Lampert C. 2021.Zero-Shot Learning. In: Computer Vision. , 1395–1397.","apa":"Lampert, C. (2021). Zero-Shot Learning. In K. Ikeuchi (Ed.), Computer Vision (2nd ed., pp. 1395–1397). Cham: Springer. https://doi.org/10.1007/978-3-030-63416-2_874","ieee":"C. Lampert, “Zero-Shot Learning,” in Computer Vision, 2nd ed., K. Ikeuchi, Ed. Cham: Springer, 2021, pp. 1395–1397.","ama":"Lampert C. Zero-Shot Learning. In: Ikeuchi K, ed. Computer Vision. 2nd ed. Cham: Springer; 2021:1395-1397. doi:10.1007/978-3-030-63416-2_874"},"quality_controlled":"1","page":"1395-1397","month":"10","day":"13","publication_identifier":{"eisbn":["9783030634162"],"isbn":["9783030634155"]},"article_processing_charge":"No"},{"oa_version":"Preprint","date_updated":"2021-01-12T08:16:44Z","date_created":"2020-06-29T23:55:23Z","author":[{"last_name":"Anciukevicius","first_name":"Titas","full_name":"Anciukevicius, Titas"},{"full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph"},{"full_name":"Henderson, Paul M","orcid":"0000-0002-5198-7445","id":"13C09E74-18D9-11E9-8878-32CFE5697425","last_name":"Henderson","first_name":"Paul M"}],"department":[{"_id":"ChLa"}],"status":"public","title":"Object-centric image generation with factored depths, locations, and appearances","ddc":["004"],"publication_status":"submitted","_id":"8063","year":"2020","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","license":"https://creativecommons.org/licenses/by-sa/4.0/","abstract":[{"lang":"eng","text":"We present a generative model of images that explicitly reasons over the set\r\nof objects they show. Our model learns a structured latent representation that\r\nseparates objects from each other and from the background; unlike prior works,\r\nit explicitly represents the 2D position and depth of each object, as well as\r\nan embedding of its segmentation mask and appearance. The model can be trained\r\nfrom images alone in a purely unsupervised fashion without the need for object\r\nmasks or depth information. Moreover, it always generates complete objects,\r\neven though a significant fraction of training images contain occlusions.\r\nFinally, we show that our model can infer decompositions of novel images into\r\ntheir constituent objects, including accurate prediction of depth ordering and\r\nsegmentation of occluded parts."}],"type":"preprint","article_number":"2004.00642","language":[{"iso":"eng"}],"date_published":"2020-04-01T00:00:00Z","main_file_link":[{"url":"https://arxiv.org/abs/2004.00642","open_access":"1"}],"tmp":{"short":"CC BY-SA (4.0)","image":"/images/cc_by_sa.png","name":"Creative Commons Attribution-ShareAlike 4.0 International Public License (CC BY-SA 4.0)","legal_code_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode"},"external_id":{"arxiv":["2004.00642"]},"citation":{"ama":"Anciukevicius T, Lampert C, Henderson PM. Object-centric image generation with factored depths, locations, and appearances. arXiv.","ieee":"T. Anciukevicius, C. Lampert, and P. M. Henderson, “Object-centric image generation with factored depths, locations, and appearances,” arXiv. .","apa":"Anciukevicius, T., Lampert, C., & Henderson, P. M. (n.d.). Object-centric image generation with factored depths, locations, and appearances. arXiv.","ista":"Anciukevicius T, Lampert C, Henderson PM. Object-centric image generation with factored depths, locations, and appearances. arXiv, 2004.00642.","short":"T. Anciukevicius, C. Lampert, P.M. Henderson, ArXiv (n.d.).","mla":"Anciukevicius, Titas, et al. “Object-Centric Image Generation with Factored Depths, Locations, and Appearances.” ArXiv, 2004.00642.","chicago":"Anciukevicius, Titas, Christoph Lampert, and Paul M Henderson. “Object-Centric Image Generation with Factored Depths, Locations, and Appearances.” ArXiv, n.d."},"oa":1,"publication":"arXiv","article_processing_charge":"No","month":"04","day":"01"},{"month":"07","publication_identifier":{"isbn":["9781713829546"]},"external_id":{"arxiv":["2007.06705"]},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2007.06705"}],"oa":1,"quality_controlled":"1","conference":{"name":"NeurIPS: Neural Information Processing Systems","start_date":"2020-12-06","location":"Vancouver, Canada","end_date":"2020-12-12"},"acknowledged_ssus":[{"_id":"ScienComp"}],"language":[{"iso":"eng"}],"acknowledgement":"This research was supported by the Scientific Service Units (SSU) of IST Austria through resources\r\nprovided by Scientific Computing (SciComp). PH is employed part-time by Blackford Analysis, but\r\nthey did not support this project in any way.","year":"2020","publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"Curran Associates","author":[{"last_name":"Henderson","first_name":"Paul M","orcid":"0000-0002-5198-7445","id":"13C09E74-18D9-11E9-8878-32CFE5697425","full_name":"Henderson, Paul M"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"date_updated":"2023-04-25T09:49:58Z","date_created":"2020-07-31T16:59:19Z","volume":33,"day":"07","article_processing_charge":"No","publication":"34th Conference on Neural Information Processing Systems","citation":{"chicago":"Henderson, Paul M, and Christoph Lampert. “Unsupervised Object-Centric Video Generation and Decomposition in 3D.” In 34th Conference on Neural Information Processing Systems, 33:3106–3117. Curran Associates, 2020.","short":"P.M. Henderson, C. Lampert, in:, 34th Conference on Neural Information Processing Systems, Curran Associates, 2020, pp. 3106–3117.","mla":"Henderson, Paul M., and Christoph Lampert. “Unsupervised Object-Centric Video Generation and Decomposition in 3D.” 34th Conference on Neural Information Processing Systems, vol. 33, Curran Associates, 2020, pp. 3106–3117.","apa":"Henderson, P. M., & Lampert, C. (2020). Unsupervised object-centric video generation and decomposition in 3D. In 34th Conference on Neural Information Processing Systems (Vol. 33, pp. 3106–3117). Vancouver, Canada: Curran Associates.","ieee":"P. M. Henderson and C. Lampert, “Unsupervised object-centric video generation and decomposition in 3D,” in 34th Conference on Neural Information Processing Systems, Vancouver, Canada, 2020, vol. 33, pp. 3106–3117.","ista":"Henderson PM, Lampert C. 2020. Unsupervised object-centric video generation and decomposition in 3D. 34th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems vol. 33, 3106–3117.","ama":"Henderson PM, Lampert C. Unsupervised object-centric video generation and decomposition in 3D. In: 34th Conference on Neural Information Processing Systems. Vol 33. Curran Associates; 2020:3106–3117."},"page":"3106–3117","date_published":"2020-07-07T00:00:00Z","type":"conference","abstract":[{"text":"A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that\r\ngives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to\r\ngenerate coherent 3D scenes containing several moving objects. We conduct detailed experiments on two datasets, going beyond the visual complexity supported by state-of-the-art generative approaches. We evaluate our method on\r\ndepth-prediction and 3D object detection---tasks which cannot be addressed by those earlier works---and show it out-performs them even on 2D instance segmentation and tracking.","lang":"eng"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"8188","status":"public","title":"Unsupervised object-centric video generation and decomposition in 3D","intvolume":" 33","oa_version":"Preprint"},{"language":[{"iso":"eng"}],"doi":"10.1007/s11263-019-01219-8","project":[{"name":"IST Austria Open Access Fund","_id":"B67AFEDC-15C9-11EA-A837-991A96BB2854"}],"isi":1,"quality_controlled":"1","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"external_id":{"arxiv":["1901.06447"],"isi":["000491042100002"]},"oa":1,"publication_identifier":{"eissn":["1573-1405"],"issn":["0920-5691"]},"month":"04","volume":128,"date_created":"2019-10-17T13:38:20Z","date_updated":"2023-08-17T14:01:16Z","author":[{"first_name":"Paul M","last_name":"Henderson","id":"13C09E74-18D9-11E9-8878-32CFE5697425","orcid":"0000-0002-5198-7445","full_name":"Henderson, Paul M"},{"full_name":"Ferrari, Vittorio","last_name":"Ferrari","first_name":"Vittorio"}],"publisher":"Springer Nature","department":[{"_id":"ChLa"}],"publication_status":"published","year":"2020","acknowledgement":"Open access funding provided by Institute of Science and Technology (IST Austria).","file_date_updated":"2020-07-14T12:47:46Z","date_published":"2020-04-01T00:00:00Z","page":"835-854","article_type":"original","citation":{"chicago":"Henderson, Paul M, and Vittorio Ferrari. “Learning Single-Image 3D Reconstruction by Generative Modelling of Shape, Pose and Shading.” International Journal of Computer Vision. Springer Nature, 2020. https://doi.org/10.1007/s11263-019-01219-8.","short":"P.M. Henderson, V. Ferrari, International Journal of Computer Vision 128 (2020) 835–854.","mla":"Henderson, Paul M., and Vittorio Ferrari. “Learning Single-Image 3D Reconstruction by Generative Modelling of Shape, Pose and Shading.” International Journal of Computer Vision, vol. 128, Springer Nature, 2020, pp. 835–54, doi:10.1007/s11263-019-01219-8.","ieee":"P. M. Henderson and V. Ferrari, “Learning single-image 3D reconstruction by generative modelling of shape, pose and shading,” International Journal of Computer Vision, vol. 128. Springer Nature, pp. 835–854, 2020.","apa":"Henderson, P. M., & Ferrari, V. (2020). Learning single-image 3D reconstruction by generative modelling of shape, pose and shading. International Journal of Computer Vision. Springer Nature. https://doi.org/10.1007/s11263-019-01219-8","ista":"Henderson PM, Ferrari V. 2020. Learning single-image 3D reconstruction by generative modelling of shape, pose and shading. International Journal of Computer Vision. 128, 835–854.","ama":"Henderson PM, Ferrari V. Learning single-image 3D reconstruction by generative modelling of shape, pose and shading. International Journal of Computer Vision. 2020;128:835-854. doi:10.1007/s11263-019-01219-8"},"publication":"International Journal of Computer Vision","article_processing_charge":"Yes (via OA deal)","has_accepted_license":"1","day":"01","scopus_import":"1","oa_version":"Published Version","file":[{"access_level":"open_access","file_name":"2019_CompVision_Henderson.pdf","file_size":2243134,"content_type":"application/pdf","creator":"dernst","relation":"main_file","file_id":"6973","checksum":"a0f05dd4f5f64e4f713d8d9d4b5b1e3f","date_updated":"2020-07-14T12:47:46Z","date_created":"2019-10-25T10:28:29Z"}],"intvolume":" 128","ddc":["004"],"status":"public","title":"Learning single-image 3D reconstruction by generative modelling of shape, pose and shading","_id":"6952","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","abstract":[{"lang":"eng","text":"We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches rely on 3D supervision, annotation of 2D images with keypoints or poses, and/or training with multiple views of each object instance. Our framework is very general: it can be trained in similar settings to existing approaches, while also supporting weaker supervision. Importantly, it can be trained purely from 2D images, without pose annotations, and with only a single view per instance. We employ meshes as an output representation, instead of voxels used in most prior work. This allows us to reason over lighting parameters and exploit shading information during training, which previous 2D-supervised methods cannot. Thus, our method can learn to generate and reconstruct concave object classes. We evaluate our approach in various settings, showing that: (i) it learns to disentangle shape from pose and lighting; (ii) using shading in the loss improves performance compared to just silhouettes; (iii) when using a standard single white light, our model outperforms state-of-the-art 2D-supervised methods, both with and without pose supervision, thanks to exploiting shading cues; (iv) performance improves further when using multiple coloured lights, even approaching that of state-of-the-art 3D-supervised methods; (v) shapes produced by our model capture smooth surfaces and fine details better than voxel-based approaches; and (vi) our approach supports concave classes such as bathtubs and sofas, which methods based on silhouettes cannot learn."}],"type":"journal_article"},{"quality_controlled":"1","external_id":{"arxiv":["2004.12623"]},"oa":1,"main_file_link":[{"url":"https://arxiv.org/abs/2004.12623","open_access":"1"}],"language":[{"iso":"eng"}],"conference":{"name":"WACV: Winter Conference on Applications of Computer Vision","location":" Snowmass Village, CO, United States","start_date":"2020-03-01","end_date":"2020-03-05"},"doi":"10.1109/WACV45572.2020.9093288","month":"03","publication_identifier":{"isbn":["9781728165530"]},"publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"IEEE","year":"2020","date_created":"2020-06-07T22:00:53Z","date_updated":"2023-09-07T13:16:17Z","author":[{"last_name":"Royer","first_name":"Amélie","orcid":"0000-0002-8407-0705","id":"3811D890-F248-11E8-B48F-1D18A9856A87","full_name":"Royer, Amélie"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"related_material":{"record":[{"relation":"dissertation_contains","status":"deleted","id":"8331"},{"id":"8390","status":"public","relation":"dissertation_contains"}]},"article_number":"1716-1725","publication":"IEEE Winter Conference on Applications of Computer Vision","citation":{"short":"A. Royer, C. Lampert, in:, IEEE Winter Conference on Applications of Computer Vision, IEEE, 2020.","mla":"Royer, Amélie, and Christoph Lampert. “Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios.” IEEE Winter Conference on Applications of Computer Vision, 1716–1725, IEEE, 2020, doi:10.1109/WACV45572.2020.9093288.","chicago":"Royer, Amélie, and Christoph Lampert. “Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios.” In IEEE Winter Conference on Applications of Computer Vision. IEEE, 2020. https://doi.org/10.1109/WACV45572.2020.9093288.","ama":"Royer A, Lampert C. Localizing grouped instances for efficient detection in low-resource scenarios. In: IEEE Winter Conference on Applications of Computer Vision. IEEE; 2020. doi:10.1109/WACV45572.2020.9093288","ieee":"A. Royer and C. Lampert, “Localizing grouped instances for efficient detection in low-resource scenarios,” in IEEE Winter Conference on Applications of Computer Vision, Snowmass Village, CO, United States, 2020.","apa":"Royer, A., & Lampert, C. (2020). Localizing grouped instances for efficient detection in low-resource scenarios. In IEEE Winter Conference on Applications of Computer Vision. Snowmass Village, CO, United States: IEEE. https://doi.org/10.1109/WACV45572.2020.9093288","ista":"Royer A, Lampert C. 2020. Localizing grouped instances for efficient detection in low-resource scenarios. IEEE Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision, 1716–1725."},"date_published":"2020-03-01T00:00:00Z","scopus_import":1,"day":"01","article_processing_charge":"No","status":"public","title":"Localizing grouped instances for efficient detection in low-resource scenarios","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"7936","oa_version":"Preprint","type":"conference","abstract":[{"lang":"eng","text":"State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life object detection applications, for example in remote sensing, instead require dealing with large images that contain only a few small objects of a single class, scattered heterogeneously across the space. In addition, they are often subject to strict computational constraints, such as limited battery capacity and computing power.To tackle these more practical scenarios, we propose a novel flexible detection scheme that efficiently adapts to variable object sizes and densities: We rely on a sequence of detection stages, each of which has the ability to predict groups of objects as well as individuals. Similar to a detection cascade, this multi-stage architecture spares computational effort by discarding large irrelevant regions of the image early during the detection process. The ability to group objects provides further computational and memory savings, as it allows working with lower image resolutions in early stages, where groups are more easily detected than individuals, as they are more salient. We report experimental results on two aerial image datasets, and show that the proposed method is as accurate yet computationally more efficient than standard single-shot detectors, consistently across three different backbone architectures."}]},{"article_number":"2180-2189","department":[{"_id":"ChLa"}],"publisher":"IEEE","publication_status":"published","year":"2020","date_updated":"2023-09-07T13:16:17Z","date_created":"2020-06-07T22:00:53Z","related_material":{"record":[{"status":"deleted","relation":"dissertation_contains","id":"8331"},{"status":"public","relation":"dissertation_contains","id":"8390"}]},"author":[{"full_name":"Royer, Amélie","id":"3811D890-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-8407-0705","first_name":"Amélie","last_name":"Royer"},{"orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","full_name":"Lampert, Christoph"}],"publication_identifier":{"isbn":["9781728165530"]},"month":"03","quality_controlled":"1","main_file_link":[{"open_access":"1","url":"http://arxiv.org/abs/2008.11995"}],"oa":1,"external_id":{"arxiv":["2008.11995"]},"language":[{"iso":"eng"}],"doi":"10.1109/WACV45572.2020.9093635","conference":{"name":"WACV: Winter Conference on Applications of Computer Vision","location":"Snowmass Village, CO, United States","start_date":"2020-03-01","end_date":"2020-03-05"},"type":"conference","abstract":[{"lang":"eng","text":"Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually different yet semantically close source is rarely considered: This commonly happens with real-life data, which is not necessarily as clean as the training source (noise, geometric transformations, different modalities, etc.).To tackle such scenarios, we introduce a new, generalized form of fine-tuning, called flex-tuning, in which any individual unit (e.g. layer) of a network can be tuned, and the most promising one is chosen automatically. In order to make the method appealing for practical use, we propose two lightweight and faster selection procedures that prove to be good approximations in practice. We study these selection criteria empirically across a variety of domain shifts and data scarcity scenarios, and show that fine-tuning individual units, despite its simplicity, yields very good results as an adaptation technique. As it turns out, in contrast to common practice, rather than the last fully-connected unit it is best to tune an intermediate or early one in many domain- shift scenarios, which is accurately detected by flex-tuning."}],"title":"A flexible selection scheme for minimum-effort transfer learning","status":"public","_id":"7937","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"Preprint","scopus_import":"1","article_processing_charge":"No","day":"01","citation":{"mla":"Royer, Amélie, and Christoph Lampert. “A Flexible Selection Scheme for Minimum-Effort Transfer Learning.” 2020 IEEE Winter Conference on Applications of Computer Vision, 2180–2189, IEEE, 2020, doi:10.1109/WACV45572.2020.9093635.","short":"A. Royer, C. Lampert, in:, 2020 IEEE Winter Conference on Applications of Computer Vision, IEEE, 2020.","chicago":"Royer, Amélie, and Christoph Lampert. “A Flexible Selection Scheme for Minimum-Effort Transfer Learning.” In 2020 IEEE Winter Conference on Applications of Computer Vision. IEEE, 2020. https://doi.org/10.1109/WACV45572.2020.9093635.","ama":"Royer A, Lampert C. A flexible selection scheme for minimum-effort transfer learning. In: 2020 IEEE Winter Conference on Applications of Computer Vision. IEEE; 2020. doi:10.1109/WACV45572.2020.9093635","ista":"Royer A, Lampert C. 2020. A flexible selection scheme for minimum-effort transfer learning. 2020 IEEE Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision, 2180–2189.","apa":"Royer, A., & Lampert, C. (2020). A flexible selection scheme for minimum-effort transfer learning. In 2020 IEEE Winter Conference on Applications of Computer Vision. Snowmass Village, CO, United States: IEEE. https://doi.org/10.1109/WACV45572.2020.9093635","ieee":"A. Royer and C. Lampert, “A flexible selection scheme for minimum-effort transfer learning,” in 2020 IEEE Winter Conference on Applications of Computer Vision, Snowmass Village, CO, United States, 2020."},"publication":"2020 IEEE Winter Conference on Applications of Computer Vision","date_published":"2020-03-01T00:00:00Z"},{"external_id":{"arxiv":["1711.05139"]},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1711.05139"}],"oa":1,"quality_controlled":"1","doi":"10.1007/978-3-030-30671-7_3","language":[{"iso":"eng"}],"month":"01","publication_identifier":{"isbn":["9783030306717"]},"year":"2020","publication_status":"published","editor":[{"first_name":"Richa","last_name":"Singh","full_name":"Singh, Richa"},{"first_name":"Mayank","last_name":"Vatsa","full_name":"Vatsa, Mayank"},{"last_name":"Patel","first_name":"Vishal M.","full_name":"Patel, Vishal M."},{"full_name":"Ratha, Nalini","first_name":"Nalini","last_name":"Ratha"}],"department":[{"_id":"ChLa"}],"publisher":"Springer Nature","author":[{"full_name":"Royer, Amélie","last_name":"Royer","first_name":"Amélie","orcid":"0000-0002-8407-0705","id":"3811D890-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Bousmalis, Konstantinos","first_name":"Konstantinos","last_name":"Bousmalis"},{"full_name":"Gouws, Stephan","first_name":"Stephan","last_name":"Gouws"},{"last_name":"Bertsch","first_name":"Fred","full_name":"Bertsch, Fred"},{"last_name":"Mosseri","first_name":"Inbar","full_name":"Mosseri, Inbar"},{"last_name":"Cole","first_name":"Forrester","full_name":"Cole, Forrester"},{"full_name":"Murphy, Kevin","first_name":"Kevin","last_name":"Murphy"}],"related_material":{"record":[{"id":"8331","status":"deleted","relation":"dissertation_contains"},{"relation":"dissertation_contains","status":"public","id":"8390"}]},"date_created":"2020-07-05T22:00:46Z","date_updated":"2023-09-07T13:16:18Z","publication":"Domain Adaptation for Visual Understanding","citation":{"chicago":"Royer, Amélie, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, and Kevin Murphy. “XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings.” In Domain Adaptation for Visual Understanding, edited by Richa Singh, Mayank Vatsa, Vishal M. Patel, and Nalini Ratha, 33–49. Springer Nature, 2020. https://doi.org/10.1007/978-3-030-30671-7_3.","mla":"Royer, Amélie, et al. “XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings.” Domain Adaptation for Visual Understanding, edited by Richa Singh et al., Springer Nature, 2020, pp. 33–49, doi:10.1007/978-3-030-30671-7_3.","short":"A. Royer, K. Bousmalis, S. Gouws, F. Bertsch, I. Mosseri, F. Cole, K. Murphy, in:, R. Singh, M. Vatsa, V.M. Patel, N. Ratha (Eds.), Domain Adaptation for Visual Understanding, Springer Nature, 2020, pp. 33–49.","ista":"Royer A, Bousmalis K, Gouws S, Bertsch F, Mosseri I, Cole F, Murphy K. 2020.XGAN: Unsupervised image-to-image translation for many-to-many mappings. In: Domain Adaptation for Visual Understanding. , 33–49.","apa":"Royer, A., Bousmalis, K., Gouws, S., Bertsch, F., Mosseri, I., Cole, F., & Murphy, K. (2020). XGAN: Unsupervised image-to-image translation for many-to-many mappings. In R. Singh, M. Vatsa, V. M. Patel, & N. Ratha (Eds.), Domain Adaptation for Visual Understanding (pp. 33–49). Springer Nature. https://doi.org/10.1007/978-3-030-30671-7_3","ieee":"A. Royer et al., “XGAN: Unsupervised image-to-image translation for many-to-many mappings,” in Domain Adaptation for Visual Understanding, R. Singh, M. Vatsa, V. M. Patel, and N. Ratha, Eds. Springer Nature, 2020, pp. 33–49.","ama":"Royer A, Bousmalis K, Gouws S, et al. XGAN: Unsupervised image-to-image translation for many-to-many mappings. In: Singh R, Vatsa M, Patel VM, Ratha N, eds. Domain Adaptation for Visual Understanding. Springer Nature; 2020:33-49. doi:10.1007/978-3-030-30671-7_3"},"page":"33-49","date_published":"2020-01-08T00:00:00Z","scopus_import":"1","day":"08","article_processing_charge":"No","_id":"8092","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"XGAN: Unsupervised image-to-image translation for many-to-many mappings","status":"public","oa_version":"Preprint","type":"book_chapter","abstract":[{"lang":"eng","text":"Image translation refers to the task of mapping images from a visual domain to another. Given two unpaired collections of images, we aim to learn a mapping between the corpus-level style of each collection, while preserving semantic content shared across the two domains. We introduce xgan, a dual adversarial auto-encoder, which captures a shared representation of the common domain semantic content in an unsupervised way, while jointly learning the domain-to-domain image translations in both directions. We exploit ideas from the domain adaptation literature and define a semantic consistency loss which encourages the learned embedding to preserve semantics shared across domains. We report promising qualitative results for the task of face-to-cartoon translation. The cartoon dataset we collected for this purpose, “CartoonSet”, is also publicly available as a new benchmark for semantic style transfer at https://google.github.io/cartoonset/index.html."}]},{"type":"conference","file_date_updated":"2020-07-14T12:47:59Z","abstract":[{"lang":"eng","text":"We address the following question: How redundant is the parameterisation of ReLU networks? Specifically, we consider transformations of the weight space which leave the function implemented by the network intact. Two such transformations are known for feed-forward architectures: permutation of neurons within a layer, and positive scaling of all incoming weights of a neuron coupled with inverse scaling of its outgoing weights. In this work, we show for architectures with non-increasing widths that permutation and scaling are in fact the only function-preserving weight transformations. For any eligible architecture we give an explicit construction of a neural network such that any other network that implements the same function can be obtained from the original one by the application of permutations and rescaling. The proof relies on a geometric understanding of boundaries between linear regions of ReLU networks, and we hope the developed mathematical tools are of independent interest."}],"department":[{"_id":"ChLa"}],"status":"public","ddc":["000"],"publication_status":"published","title":"Functional vs. parametric equivalence of ReLU networks","year":"2020","_id":"7481","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","file":[{"date_updated":"2020-07-14T12:47:59Z","date_created":"2020-02-11T09:07:27Z","checksum":"8d372ea5defd8cb8fdc430111ed754a9","relation":"main_file","file_id":"7482","content_type":"application/pdf","file_size":405469,"creator":"bphuong","file_name":"main.pdf","access_level":"open_access"}],"oa_version":"Published Version","date_updated":"2023-09-07T13:29:50Z","date_created":"2020-02-11T09:07:37Z","related_material":{"record":[{"id":"9418","status":"public","relation":"dissertation_contains"}],"link":[{"relation":"supplementary_material","url":"https://iclr.cc/virtual_2020/poster_Bylx-TNKvH.html"}]},"author":[{"full_name":"Bui Thi Mai, Phuong","id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87","last_name":"Bui Thi Mai","first_name":"Phuong"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"has_accepted_license":"1","article_processing_charge":"No","day":"26","month":"04","quality_controlled":"1","citation":{"chicago":"Phuong, Mary, and Christoph Lampert. “Functional vs. Parametric Equivalence of ReLU Networks.” In 8th International Conference on Learning Representations, 2020.","short":"M. Phuong, C. Lampert, in:, 8th International Conference on Learning Representations, 2020.","mla":"Phuong, Mary, and Christoph Lampert. “Functional vs. Parametric Equivalence of ReLU Networks.” 8th International Conference on Learning Representations, 2020.","apa":"Phuong, M., & Lampert, C. (2020). Functional vs. parametric equivalence of ReLU networks. In 8th International Conference on Learning Representations. Online.","ieee":"M. Phuong and C. Lampert, “Functional vs. parametric equivalence of ReLU networks,” in 8th International Conference on Learning Representations, Online, 2020.","ista":"Phuong M, Lampert C. 2020. Functional vs. parametric equivalence of ReLU networks. 8th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","ama":"Phuong M, Lampert C. Functional vs. parametric equivalence of ReLU networks. In: 8th International Conference on Learning Representations. ; 2020."},"oa":1,"publication":"8th International Conference on Learning Representations","language":[{"iso":"eng"}],"date_published":"2020-04-26T00:00:00Z","conference":{"end_date":"2020-04-30","location":"Online","start_date":"2020-04-27","name":"ICLR: International Conference on Learning Representations"}},{"citation":{"chicago":"Konstantinov, Nikola H, Elias Frantar, Dan-Adrian Alistarh, and Christoph Lampert. “On the Sample Complexity of Adversarial Multi-Source PAC Learning.” In Proceedings of the 37th International Conference on Machine Learning, 119:5416–25. ML Research Press, 2020.","short":"N.H. Konstantinov, E. Frantar, D.-A. Alistarh, C. Lampert, in:, Proceedings of the 37th International Conference on Machine Learning, ML Research Press, 2020, pp. 5416–5425.","mla":"Konstantinov, Nikola H., et al. “On the Sample Complexity of Adversarial Multi-Source PAC Learning.” Proceedings of the 37th International Conference on Machine Learning, vol. 119, ML Research Press, 2020, pp. 5416–25.","apa":"Konstantinov, N. H., Frantar, E., Alistarh, D.-A., & Lampert, C. (2020). On the sample complexity of adversarial multi-source PAC learning. In Proceedings of the 37th International Conference on Machine Learning (Vol. 119, pp. 5416–5425). Online: ML Research Press.","ieee":"N. H. Konstantinov, E. Frantar, D.-A. Alistarh, and C. Lampert, “On the sample complexity of adversarial multi-source PAC learning,” in Proceedings of the 37th International Conference on Machine Learning, Online, 2020, vol. 119, pp. 5416–5425.","ista":"Konstantinov NH, Frantar E, Alistarh D-A, Lampert C. 2020. On the sample complexity of adversarial multi-source PAC learning. Proceedings of the 37th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 119, 5416–5425.","ama":"Konstantinov NH, Frantar E, Alistarh D-A, Lampert C. On the sample complexity of adversarial multi-source PAC learning. In: Proceedings of the 37th International Conference on Machine Learning. Vol 119. ML Research Press; 2020:5416-5425."},"publication":"Proceedings of the 37th International Conference on Machine Learning","page":"5416-5425","date_published":"2020-07-12T00:00:00Z","scopus_import":"1","article_processing_charge":"No","has_accepted_license":"1","day":"12","_id":"8724","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","intvolume":" 119","status":"public","title":"On the sample complexity of adversarial multi-source PAC learning","ddc":["000"],"oa_version":"Published Version","file":[{"access_level":"open_access","file_name":"2020_PMLR_Konstantinov.pdf","creator":"dernst","content_type":"application/pdf","file_size":281286,"file_id":"9120","relation":"main_file","success":1,"checksum":"cc755d0054bc4b2be778ea7aa7884d2f","date_created":"2021-02-15T09:00:01Z","date_updated":"2021-02-15T09:00:01Z"}],"type":"conference","abstract":[{"text":"We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing and collaborative learning paradigms. Specifically, we analyze the situation in which a learning system obtains datasets from multiple sources, some of which might be biased or even adversarially perturbed. It is\r\nknown that in the single-source case, an adversary with the power to corrupt a fixed fraction of the training data can prevent PAC-learnability, that is, even in the limit of infinitely much training data, no learning system can approach the optimal test error. In this work we show that, surprisingly, the same is not true in the multi-source setting, where the adversary can arbitrarily\r\ncorrupt a fixed fraction of the data sources. Our main results are a generalization bound that provides finite-sample guarantees for this learning setting, as well as corresponding lower bounds. Besides establishing PAC-learnability our results also show that in a cooperative learning setting sharing data with other parties has provable benefits, even if some\r\nparticipants are malicious. ","lang":"eng"}],"oa":1,"external_id":{"arxiv":["2002.10384"]},"project":[{"name":"Elastic Coordination for Scalable Machine Learning","call_identifier":"H2020","grant_number":"805223","_id":"268A44D6-B435-11E9-9278-68D0E5697425"}],"quality_controlled":"1","conference":{"name":"ICML: International Conference on Machine Learning","location":"Online","start_date":"2020-07-12","end_date":"2020-07-18"},"language":[{"iso":"eng"}],"acknowledged_ssus":[{"_id":"ScienComp"}],"publication_identifier":{"issn":["2640-3498"]},"month":"07","year":"2020","acknowledgement":"Dan Alistarh is supported in part by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 805223 ScaleML). This research was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp).","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"publisher":"ML Research Press","publication_status":"published","related_material":{"record":[{"id":"10799","relation":"dissertation_contains","status":"public"}],"link":[{"url":"http://proceedings.mlr.press/v119/konstantinov20a/konstantinov20a-supp.pdf","relation":"supplementary_material"}]},"author":[{"full_name":"Konstantinov, Nikola H","last_name":"Konstantinov","first_name":"Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Frantar","first_name":"Elias","id":"09a8f98d-ec99-11ea-ae11-c063a7b7fe5f","full_name":"Frantar, Elias"},{"orcid":"0000-0003-3650-940X","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","last_name":"Alistarh","first_name":"Dan-Adrian","full_name":"Alistarh, Dan-Adrian"},{"orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","full_name":"Lampert, Christoph"}],"volume":119,"date_updated":"2023-09-07T13:42:08Z","date_created":"2020-11-05T15:25:58Z","ec_funded":1,"file_date_updated":"2021-02-15T09:00:01Z"},{"article_processing_charge":"No","has_accepted_license":"1","day":"14","date_published":"2020-09-14T00:00:00Z","page":"197","citation":{"short":"A. Royer, Leveraging Structure in Computer Vision Tasks for Flexible Deep Learning Models, Institute of Science and Technology Austria, 2020.","mla":"Royer, Amélie. Leveraging Structure in Computer Vision Tasks for Flexible Deep Learning Models. Institute of Science and Technology Austria, 2020, doi:10.15479/AT:ISTA:8390.","chicago":"Royer, Amélie. “Leveraging Structure in Computer Vision Tasks for Flexible Deep Learning Models.” Institute of Science and Technology Austria, 2020. https://doi.org/10.15479/AT:ISTA:8390.","ama":"Royer A. Leveraging structure in Computer Vision tasks for flexible Deep Learning models. 2020. doi:10.15479/AT:ISTA:8390","apa":"Royer, A. (2020). Leveraging structure in Computer Vision tasks for flexible Deep Learning models. Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:8390","ieee":"A. Royer, “Leveraging structure in Computer Vision tasks for flexible Deep Learning models,” Institute of Science and Technology Austria, 2020.","ista":"Royer A. 2020. Leveraging structure in Computer Vision tasks for flexible Deep Learning models. Institute of Science and Technology Austria."},"abstract":[{"lang":"eng","text":"Deep neural networks have established a new standard for data-dependent feature extraction pipelines in the Computer Vision literature. Despite their remarkable performance in the standard supervised learning scenario, i.e. when models are trained with labeled data and tested on samples that follow a similar distribution, neural networks have been shown to struggle with more advanced generalization abilities, such as transferring knowledge across visually different domains, or generalizing to new unseen combinations of known concepts. In this thesis we argue that, in contrast to the usual black-box behavior of neural networks, leveraging more structured internal representations is a promising direction\r\nfor tackling such problems. In particular, we focus on two forms of structure. First, we tackle modularity: We show that (i) compositional architectures are a natural tool for modeling reasoning tasks, in that they efficiently capture their combinatorial nature, which is key for generalizing beyond the compositions seen during training. We investigate how to to learn such models, both formally and experimentally, for the task of abstract visual reasoning. Then, we show that (ii) in some settings, modularity allows us to efficiently break down complex tasks into smaller, easier, modules, thereby improving computational efficiency; We study this behavior in the context of generative models for colorization, as well as for small objects detection. Secondly, we investigate the inherently layered structure of representations learned by neural networks, and analyze its role in the context of transfer learning and domain adaptation across visually\r\ndissimilar domains. "}],"alternative_title":["ISTA Thesis"],"type":"dissertation","oa_version":"Published Version","file":[{"file_size":30224591,"content_type":"application/pdf","creator":"dernst","access_level":"open_access","file_name":"2020_Thesis_Royer.pdf","checksum":"c914d2f88846032f3d8507734861b6ee","success":1,"date_updated":"2020-09-14T13:39:14Z","date_created":"2020-09-14T13:39:14Z","relation":"main_file","file_id":"8391"},{"creator":"dernst","content_type":"application/x-zip-compressed","file_size":74227627,"file_name":"thesis_sources.zip","access_level":"closed","date_updated":"2020-09-14T13:39:17Z","date_created":"2020-09-14T13:39:17Z","checksum":"ae98fb35d912cff84a89035ae5794d3c","file_id":"8392","relation":"main_file"}],"title":"Leveraging structure in Computer Vision tasks for flexible Deep Learning models","status":"public","ddc":["000"],"_id":"8390","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","publication_identifier":{"issn":["2663-337X"],"isbn":["978-3-99078-007-7"]},"month":"09","language":[{"iso":"eng"}],"degree_awarded":"PhD","supervisor":[{"orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","full_name":"Lampert, Christoph"}],"acknowledged_ssus":[{"_id":"CampIT"},{"_id":"ScienComp"}],"doi":"10.15479/AT:ISTA:8390","tmp":{"name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode","image":"/images/cc_by_nc_sa.png","short":"CC BY-NC-SA (4.0)"},"oa":1,"license":"https://creativecommons.org/licenses/by-nc-sa/4.0/","file_date_updated":"2020-09-14T13:39:17Z","date_created":"2020-09-14T13:42:09Z","date_updated":"2023-10-16T10:04:02Z","related_material":{"record":[{"status":"public","relation":"part_of_dissertation","id":"7936"},{"relation":"part_of_dissertation","status":"public","id":"7937"},{"id":"8193","relation":"part_of_dissertation","status":"public"},{"status":"public","relation":"part_of_dissertation","id":"8092"},{"status":"public","relation":"part_of_dissertation","id":"911"}]},"author":[{"last_name":"Royer","first_name":"Amélie","orcid":"0000-0002-8407-0705","id":"3811D890-F248-11E8-B48F-1D18A9856A87","full_name":"Royer, Amélie"}],"publisher":"Institute of Science and Technology Austria","department":[{"_id":"ChLa"}],"publication_status":"published","acknowledgement":"Last but not least, I would like to acknowledge the support of the IST IT and scientific computing team for helping provide a great work environment.","year":"2020"},{"abstract":[{"lang":"eng","text":"Numerous methods have been proposed for probabilistic generative modelling of\r\n3D objects. However, none of these is able to produce textured objects, which\r\nrenders them of limited use for practical tasks. In this work, we present the\r\nfirst generative model of textured 3D meshes. Training such a model would\r\ntraditionally require a large dataset of textured meshes, but unfortunately,\r\nexisting datasets of meshes lack detailed textures. We instead propose a new\r\ntraining methodology that allows learning from collections of 2D images without\r\nany 3D information. To do so, we train our model to explain a distribution of\r\nimages by modelling each image as a 3D foreground object placed in front of a\r\n2D background. Thus, it learns to generate meshes that when rendered, produce\r\nimages similar to those in its training set.\r\n A well-known problem when generating meshes with deep networks is the\r\nemergence of self-intersections, which are problematic for many use-cases. As a\r\nsecond contribution we therefore introduce a new generation process for 3D\r\nmeshes that guarantees no self-intersections arise, based on the physical\r\nintuition that faces should push one another out of the way as they move.\r\n We conduct extensive experiments on our approach, reporting quantitative and\r\nqualitative results on both synthetic data and natural images. These show our\r\nmethod successfully learns to generate plausible and diverse textured 3D\r\nsamples for five challenging object classes."}],"type":"conference","file":[{"date_created":"2020-07-31T16:57:12Z","date_updated":"2020-07-31T16:57:12Z","success":1,"relation":"main_file","file_id":"8187","content_type":"application/pdf","file_size":10262773,"creator":"phenders","file_name":"paper.pdf","access_level":"open_access"}],"oa_version":"Submitted Version","ddc":["004"],"title":"Leveraging 2D data to learn textured 3D mesh generation","status":"public","_id":"8186","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","has_accepted_license":"1","article_processing_charge":"No","day":"01","scopus_import":"1","date_published":"2020-07-01T00:00:00Z","page":"7498-7507","citation":{"ama":"Henderson PM, Tsiminaki V, Lampert C. Leveraging 2D data to learn textured 3D mesh generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE; 2020:7498-7507. doi:10.1109/CVPR42600.2020.00752","ieee":"P. M. Henderson, V. Tsiminaki, and C. Lampert, “Leveraging 2D data to learn textured 3D mesh generation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual, 2020, pp. 7498–7507.","apa":"Henderson, P. M., Tsiminaki, V., & Lampert, C. (2020). Leveraging 2D data to learn textured 3D mesh generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7498–7507). Virtual: IEEE. https://doi.org/10.1109/CVPR42600.2020.00752","ista":"Henderson PM, Tsiminaki V, Lampert C. 2020. Leveraging 2D data to learn textured 3D mesh generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 7498–7507.","short":"P.M. Henderson, V. Tsiminaki, C. Lampert, in:, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2020, pp. 7498–7507.","mla":"Henderson, Paul M., et al. “Leveraging 2D Data to Learn Textured 3D Mesh Generation.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2020, pp. 7498–507, doi:10.1109/CVPR42600.2020.00752.","chicago":"Henderson, Paul M, Vagia Tsiminaki, and Christoph Lampert. “Leveraging 2D Data to Learn Textured 3D Mesh Generation.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7498–7507. IEEE, 2020. https://doi.org/10.1109/CVPR42600.2020.00752."},"publication":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","file_date_updated":"2020-07-31T16:57:12Z","date_created":"2020-07-31T16:53:49Z","date_updated":"2023-10-17T07:37:11Z","author":[{"full_name":"Henderson, Paul M","id":"13C09E74-18D9-11E9-8878-32CFE5697425","orcid":"0000-0002-5198-7445","first_name":"Paul M","last_name":"Henderson"},{"full_name":"Tsiminaki, Vagia","first_name":"Vagia","last_name":"Tsiminaki"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"department":[{"_id":"ChLa"}],"publisher":"IEEE","publication_status":"published","year":"2020","publication_identifier":{"eissn":["2575-7075"],"eisbn":["9781728171685"]},"month":"07","language":[{"iso":"eng"}],"doi":"10.1109/CVPR42600.2020.00752","conference":{"location":"Virtual","start_date":"2020-06-14","end_date":"2020-06-19","name":"CVPR: Conference on Computer Vision and Pattern Recognition"},"quality_controlled":"1","external_id":{"arxiv":["2004.04180"]},"main_file_link":[{"url":"https://openaccess.thecvf.com/content_CVPR_2020/papers/Henderson_Leveraging_2D_Data_to_Learn_Textured_3D_Mesh_Generation_CVPR_2020_paper.pdf","open_access":"1"}],"oa":1},{"type":"journal_article","abstract":[{"lang":"eng","text":"We study the problem of automatically detecting if a given multi-class classifier operates outside of its specifications (out-of-specs), i.e. on input data from a different distribution than what it was trained for. This is an important problem to solve on the road towards creating reliable computer vision systems for real-world applications, because the quality of a classifier’s predictions cannot be guaranteed if it operates out-of-specs. Previously proposed methods for out-of-specs detection make decisions on the level of single inputs. This, however, is insufficient to achieve low false positive rate and high false negative rates at the same time. In this work, we describe a new procedure named KS(conf), based on statistical reasoning. Its main component is a classical Kolmogorov–Smirnov test that is applied to the set of predicted confidence values for batches of samples. Working with batches instead of single samples allows increasing the true positive rate without negatively affecting the false positive rate, thereby overcoming a crucial limitation of single sample tests. We show by extensive experiments using a variety of convolutional network architectures and datasets that KS(conf) reliably detects out-of-specs situations even under conditions where other tests fail. It furthermore has a number of properties that make it an excellent candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with any classifier that outputs confidence scores, and requires no a priori knowledge about how the data distribution could change."}],"issue":"4","_id":"6944","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","status":"public","ddc":["004"],"title":"KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications","intvolume":" 128","oa_version":"Published Version","file":[{"relation":"main_file","file_id":"7110","date_updated":"2020-07-14T12:47:45Z","date_created":"2019-11-26T10:30:02Z","checksum":"155e63edf664dcacb3bdc1c2223e606f","file_name":"2019_IJCV_Sun.pdf","access_level":"open_access","file_size":1715072,"content_type":"application/pdf","creator":"dernst"}],"scopus_import":"1","day":"01","has_accepted_license":"1","article_processing_charge":"Yes (via OA deal)","publication":"International Journal of Computer Vision","citation":{"ista":"Sun R, Lampert C. 2020. KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications. International Journal of Computer Vision. 128(4), 970–995.","apa":"Sun, R., & Lampert, C. (2020). KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications. International Journal of Computer Vision. Springer Nature. https://doi.org/10.1007/s11263-019-01232-x","ieee":"R. Sun and C. Lampert, “KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications,” International Journal of Computer Vision, vol. 128, no. 4. Springer Nature, pp. 970–995, 2020.","ama":"Sun R, Lampert C. KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications. International Journal of Computer Vision. 2020;128(4):970-995. doi:10.1007/s11263-019-01232-x","chicago":"Sun, Rémy, and Christoph Lampert. “KS(Conf): A Light-Weight Test If a Multiclass Classifier Operates Outside of Its Specifications.” International Journal of Computer Vision. Springer Nature, 2020. https://doi.org/10.1007/s11263-019-01232-x.","mla":"Sun, Rémy, and Christoph Lampert. “KS(Conf): A Light-Weight Test If a Multiclass Classifier Operates Outside of Its Specifications.” International Journal of Computer Vision, vol. 128, no. 4, Springer Nature, 2020, pp. 970–95, doi:10.1007/s11263-019-01232-x.","short":"R. Sun, C. Lampert, International Journal of Computer Vision 128 (2020) 970–995."},"article_type":"original","page":"970-995","date_published":"2020-04-01T00:00:00Z","file_date_updated":"2020-07-14T12:47:45Z","ec_funded":1,"year":"2020","publication_status":"published","publisher":"Springer Nature","department":[{"_id":"ChLa"}],"author":[{"full_name":"Sun, Rémy","last_name":"Sun","first_name":"Rémy"},{"first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph"}],"related_material":{"record":[{"id":"6482","status":"public","relation":"earlier_version"}],"link":[{"relation":"erratum","url":"https://doi.org/10.1007/s11263-019-01262-5"}]},"date_created":"2019-10-14T09:14:28Z","date_updated":"2024-02-22T14:57:30Z","volume":128,"month":"04","publication_identifier":{"issn":["0920-5691"],"eissn":["1573-1405"]},"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"oa":1,"external_id":{"isi":["000494406800001"]},"quality_controlled":"1","isi":1,"project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"},{"name":"IST Austria Open Access Fund","_id":"B67AFEDC-15C9-11EA-A837-991A96BB2854"}],"doi":"10.1007/s11263-019-01232-x","language":[{"iso":"eng"}]},{"language":[{"iso":"ger"}],"doi":"10.1007/978-3-658-26763-6","date_published":"2019-10-30T00:00:00Z","page":"XIV, 245","quality_controlled":"1","citation":{"ista":"Kersting K, Lampert C, Rothkopf C eds. 2019. Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt 1st ed., Wiesbaden: Springer Nature, XIV, 245p.","ieee":"K. Kersting, C. Lampert, and C. Rothkopf, Eds., Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt, 1st ed. Wiesbaden: Springer Nature, 2019.","apa":"Kersting, K., Lampert, C., & Rothkopf, C. (Eds.). (2019). Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt (1st ed.). Wiesbaden: Springer Nature. https://doi.org/10.1007/978-3-658-26763-6","ama":"Kersting K, Lampert C, Rothkopf C, eds. Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt. 1st ed. Wiesbaden: Springer Nature; 2019. doi:10.1007/978-3-658-26763-6","chicago":"Kersting, Kristian, Christoph Lampert, and Constantin Rothkopf, eds. Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt. 1st ed. Wiesbaden: Springer Nature, 2019. https://doi.org/10.1007/978-3-658-26763-6.","mla":"Kersting, Kristian, et al., editors. Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt. 1st ed., Springer Nature, 2019, doi:10.1007/978-3-658-26763-6.","short":"K. Kersting, C. Lampert, C. Rothkopf, eds., Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt, 1st ed., Springer Nature, Wiesbaden, 2019."},"article_processing_charge":"No","publication_identifier":{"eisbn":["978-3-658-26763-6"],"isbn":["978-3-658-26762-9"]},"month":"10","day":"30","oa_version":"None","date_created":"2019-12-11T14:15:56Z","date_updated":"2021-12-22T14:40:58Z","edition":"1","related_material":{"link":[{"url":"https://ist.ac.at/en/news/book-release-how-machines-learn/","relation":"press_release","description":"News on IST Website"}]},"editor":[{"first_name":"Kristian","last_name":"Kersting","full_name":"Kersting, Kristian"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert"},{"last_name":"Rothkopf","first_name":"Constantin","full_name":"Rothkopf, Constantin"}],"department":[{"_id":"ChLa"}],"publisher":"Springer Nature","publication_status":"published","title":"Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt","status":"public","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","_id":"7171","year":"2019","abstract":[{"lang":"ger","text":"Wissen Sie, was sich hinter künstlicher Intelligenz und maschinellem Lernen verbirgt? \r\nDieses Sachbuch erklärt Ihnen leicht verständlich und ohne komplizierte Formeln die grundlegenden Methoden und Vorgehensweisen des maschinellen Lernens. Mathematisches Vorwissen ist dafür nicht nötig. Kurzweilig und informativ illustriert Lisa, die Protagonistin des Buches, diese anhand von Alltagssituationen. \r\nEin Buch für alle, die in Diskussionen über Chancen und Risiken der aktuellen Entwicklung der künstlichen Intelligenz und des maschinellen Lernens mit Faktenwissen punkten möchten. Auch für Schülerinnen und Schüler geeignet!"}],"place":"Wiesbaden","type":"book_editor"},{"publication_identifier":{"issn":["0302-9743"],"eisbn":["9783030302818"],"isbn":["9783030302801"]},"month":"09","project":[{"name":"Game Theory","call_identifier":"FWF","grant_number":"S11407","_id":"25863FF4-B435-11E9-9278-68D0E5697425"},{"grant_number":"S11402-N23","_id":"25F2ACDE-B435-11E9-9278-68D0E5697425","call_identifier":"FWF","name":"Rigorous Systems Engineering"},{"name":"Efficient Algorithms for Computer Aided Verification","grant_number":"ICT15-003","_id":"25892FC0-B435-11E9-9278-68D0E5697425"}],"isi":1,"quality_controlled":"1","external_id":{"arxiv":["1906.08178"],"isi":["000679281300007"]},"main_file_link":[{"url":"https://arxiv.org/abs/1906.08178","open_access":"1"}],"oa":1,"language":[{"iso":"eng"}],"doi":"10.1007/978-3-030-30281-8_7","conference":{"end_date":"2019-09-12","start_date":"2019-09-10","location":"Glasgow, United Kingdom","name":"QEST: Quantitative Evaluation of Systems"},"department":[{"_id":"KrCh"},{"_id":"ChLa"}],"publisher":"Springer Nature","publication_status":"published","year":"2019","volume":11785,"date_created":"2019-10-14T06:57:49Z","date_updated":"2023-08-30T06:59:36Z","author":[{"full_name":"Ashok, Pranav","last_name":"Ashok","first_name":"Pranav"},{"full_name":"Brázdil, Tomáš","first_name":"Tomáš","last_name":"Brázdil"},{"full_name":"Chatterjee, Krishnendu","orcid":"0000-0002-4561-241X","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","last_name":"Chatterjee","first_name":"Krishnendu"},{"full_name":"Křetínský, Jan","first_name":"Jan","last_name":"Křetínský"},{"last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"},{"orcid":"0000-0001-9036-063X","id":"3AF3DA7C-F248-11E8-B48F-1D18A9856A87","last_name":"Toman","first_name":"Viktor","full_name":"Toman, Viktor"}],"scopus_import":"1","article_processing_charge":"No","day":"04","page":"109-128","citation":{"ista":"Ashok P, Brázdil T, Chatterjee K, Křetínský J, Lampert C, Toman V. 2019. Strategy representation by decision trees with linear classifiers. 16th International Conference on Quantitative Evaluation of Systems. QEST: Quantitative Evaluation of Systems, LNCS, vol. 11785, 109–128.","apa":"Ashok, P., Brázdil, T., Chatterjee, K., Křetínský, J., Lampert, C., & Toman, V. (2019). Strategy representation by decision trees with linear classifiers. In 16th International Conference on Quantitative Evaluation of Systems (Vol. 11785, pp. 109–128). Glasgow, United Kingdom: Springer Nature. https://doi.org/10.1007/978-3-030-30281-8_7","ieee":"P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. Lampert, and V. Toman, “Strategy representation by decision trees with linear classifiers,” in 16th International Conference on Quantitative Evaluation of Systems, Glasgow, United Kingdom, 2019, vol. 11785, pp. 109–128.","ama":"Ashok P, Brázdil T, Chatterjee K, Křetínský J, Lampert C, Toman V. Strategy representation by decision trees with linear classifiers. In: 16th International Conference on Quantitative Evaluation of Systems. Vol 11785. Springer Nature; 2019:109-128. doi:10.1007/978-3-030-30281-8_7","chicago":"Ashok, Pranav, Tomáš Brázdil, Krishnendu Chatterjee, Jan Křetínský, Christoph Lampert, and Viktor Toman. “Strategy Representation by Decision Trees with Linear Classifiers.” In 16th International Conference on Quantitative Evaluation of Systems, 11785:109–28. Springer Nature, 2019. https://doi.org/10.1007/978-3-030-30281-8_7.","mla":"Ashok, Pranav, et al. “Strategy Representation by Decision Trees with Linear Classifiers.” 16th International Conference on Quantitative Evaluation of Systems, vol. 11785, Springer Nature, 2019, pp. 109–28, doi:10.1007/978-3-030-30281-8_7.","short":"P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. Lampert, V. Toman, in:, 16th International Conference on Quantitative Evaluation of Systems, Springer Nature, 2019, pp. 109–128."},"publication":"16th International Conference on Quantitative Evaluation of Systems","date_published":"2019-09-04T00:00:00Z","alternative_title":["LNCS"],"type":"conference","abstract":[{"lang":"eng","text":"Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of 𝜔 -regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees."}],"intvolume":" 11785","status":"public","title":"Strategy representation by decision trees with linear classifiers","_id":"6942","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","oa_version":"Preprint"},{"month":"09","publication_identifier":{"eissn":["1939-3539"],"issn":["0162-8828"]},"doi":"10.1109/tpami.2018.2857768","language":[{"iso":"eng"}],"oa":1,"external_id":{"isi":["000480343900015"],"arxiv":["1707.00600"]},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1707.00600"}],"isi":1,"quality_controlled":"1","author":[{"full_name":"Xian, Yongqin","last_name":"Xian","first_name":"Yongqin"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4561-241X","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"},{"full_name":"Schiele, Bernt","first_name":"Bernt","last_name":"Schiele"},{"last_name":"Akata","first_name":"Zeynep","full_name":"Akata, Zeynep"}],"date_created":"2019-06-11T14:05:59Z","date_updated":"2023-09-05T13:18:09Z","volume":41,"year":"2019","publication_status":"published","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","department":[{"_id":"ChLa"}],"day":"01","article_processing_charge":"No","scopus_import":"1","date_published":"2019-09-01T00:00:00Z","publication":"IEEE Transactions on Pattern Analysis and Machine Intelligence","citation":{"ama":"Xian Y, Lampert C, Schiele B, Akata Z. Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2019;41(9):2251-2265. doi:10.1109/tpami.2018.2857768","ista":"Xian Y, Lampert C, Schiele B, Akata Z. 2019. Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly. IEEE Transactions on Pattern Analysis and Machine Intelligence. 41(9), 2251–2265.","apa":"Xian, Y., Lampert, C., Schiele, B., & Akata, Z. (2019). Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly. IEEE Transactions on Pattern Analysis and Machine Intelligence. Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/tpami.2018.2857768","ieee":"Y. Xian, C. Lampert, B. Schiele, and Z. Akata, “Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 9. Institute of Electrical and Electronics Engineers (IEEE), pp. 2251–2265, 2019.","mla":"Xian, Yongqin, et al. “Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 9, Institute of Electrical and Electronics Engineers (IEEE), 2019, pp. 2251–65, doi:10.1109/tpami.2018.2857768.","short":"Y. Xian, C. Lampert, B. Schiele, Z. Akata, IEEE Transactions on Pattern Analysis and Machine Intelligence 41 (2019) 2251–2265.","chicago":"Xian, Yongqin, Christoph Lampert, Bernt Schiele, and Zeynep Akata. “Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Institute of Electrical and Electronics Engineers (IEEE), 2019. https://doi.org/10.1109/tpami.2018.2857768."},"article_type":"original","page":"2251 - 2265","abstract":[{"lang":"eng","text":"Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits of publicly available datasets used for this task. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Moreover, we propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2) dataset which we make publicly available both in terms of image features and the images themselves. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss in detail the limitations of the current status of the area which can be taken as a basis for advancing it."}],"issue":"9","type":"journal_article","oa_version":"Preprint","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","_id":"6554","status":"public","title":"Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly","intvolume":" 41"},{"abstract":[{"lang":"eng","text":"Multi-exit architectures, in which a stack of processing layers is interleaved with early output layers, allow the processing of a test example to stop early and thus save computation time and/or energy. In this work, we propose a new training procedure for multi-exit architectures based on the principle of knowledge distillation. The method encourage searly exits to mimic later, more accurate exits, by matching their output probabilities.\r\nExperiments on CIFAR100 and ImageNet show that distillation-based training significantly improves the accuracy of early exits while maintaining state-of-the-art accuracy for late ones. The method is particularly beneficial when training data is limited and it allows a straightforward extension to semi-supervised learning,i.e. making use of unlabeled data at training time. Moreover, it takes only afew lines to implement and incurs almost no computational overhead at training time, and none at all at test time."}],"type":"conference","oa_version":"Submitted Version","file":[{"file_size":735768,"content_type":"application/pdf","creator":"bphuong","file_name":"main.pdf","access_level":"open_access","date_created":"2020-02-11T09:06:39Z","date_updated":"2020-07-14T12:47:59Z","checksum":"7b77fb5c2d27c4c37a7612ba46a66117","relation":"main_file","file_id":"7480"}],"ddc":["000"],"status":"public","title":"Distillation-based training for multi-exit architectures","_id":"7479","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","day":"01","has_accepted_license":"1","article_processing_charge":"No","scopus_import":"1","date_published":"2019-10-01T00:00:00Z","page":"1355-1364","publication":"IEEE International Conference on Computer Vision","citation":{"ama":"Phuong M, Lampert C. Distillation-based training for multi-exit architectures. In: IEEE International Conference on Computer Vision. Vol 2019-October. IEEE; 2019:1355-1364. doi:10.1109/ICCV.2019.00144","ieee":"M. Phuong and C. Lampert, “Distillation-based training for multi-exit architectures,” in IEEE International Conference on Computer Vision, Seoul, Korea, 2019, vol. 2019–October, pp. 1355–1364.","apa":"Phuong, M., & Lampert, C. (2019). Distillation-based training for multi-exit architectures. In IEEE International Conference on Computer Vision (Vol. 2019–October, pp. 1355–1364). Seoul, Korea: IEEE. https://doi.org/10.1109/ICCV.2019.00144","ista":"Phuong M, Lampert C. 2019. Distillation-based training for multi-exit architectures. IEEE International Conference on Computer Vision. ICCV: International Conference on Computer Vision vol. 2019–October, 1355–1364.","short":"M. Phuong, C. Lampert, in:, IEEE International Conference on Computer Vision, IEEE, 2019, pp. 1355–1364.","mla":"Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit Architectures.” IEEE International Conference on Computer Vision, vol. 2019–October, IEEE, 2019, pp. 1355–64, doi:10.1109/ICCV.2019.00144.","chicago":"Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit Architectures.” In IEEE International Conference on Computer Vision, 2019–October:1355–64. IEEE, 2019. https://doi.org/10.1109/ICCV.2019.00144."},"file_date_updated":"2020-07-14T12:47:59Z","ec_funded":1,"date_updated":"2023-09-08T11:11:12Z","date_created":"2020-02-11T09:06:57Z","volume":"2019-October","author":[{"full_name":"Bui Thi Mai, Phuong","id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87","first_name":"Phuong","last_name":"Bui Thi Mai"},{"last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"}],"related_material":{"record":[{"id":"9418","relation":"dissertation_contains","status":"public"}]},"publication_status":"published","publisher":"IEEE","department":[{"_id":"ChLa"}],"year":"2019","month":"10","publication_identifier":{"isbn":["9781728148038"],"issn":["15505499"]},"language":[{"iso":"eng"}],"conference":{"location":"Seoul, Korea","start_date":"2019-10-27","end_date":"2019-11-02","name":"ICCV: International Conference on Computer Vision"},"doi":"10.1109/ICCV.2019.00144","quality_controlled":"1","isi":1,"project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"external_id":{"isi":["000531438101047"]},"oa":1},{"oa_version":"Preprint","title":"Detecting visual relationships using box attention","status":"public","_id":"7640","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","abstract":[{"text":"We propose a new model for detecting visual relationships, such as \"person riding motorcycle\" or \"bottle on table\". This task is an important step towards comprehensive structured mage understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on two datasets, V-COCO and Open Images, demonstrating strong quantitative and qualitative results.","lang":"eng"}],"type":"conference","date_published":"2019-10-01T00:00:00Z","citation":{"ista":"Kolesnikov A, Kuznetsova A, Lampert C, Ferrari V. 2019. Detecting visual relationships using box attention. Proceedings of the 2019 International Conference on Computer Vision Workshop. ICCVW: International Conference on Computer Vision Workshop, 1749–1753.","apa":"Kolesnikov, A., Kuznetsova, A., Lampert, C., & Ferrari, V. (2019). Detecting visual relationships using box attention. In Proceedings of the 2019 International Conference on Computer Vision Workshop. Seoul, South Korea: IEEE. https://doi.org/10.1109/ICCVW.2019.00217","ieee":"A. Kolesnikov, A. Kuznetsova, C. Lampert, and V. Ferrari, “Detecting visual relationships using box attention,” in Proceedings of the 2019 International Conference on Computer Vision Workshop, Seoul, South Korea, 2019.","ama":"Kolesnikov A, Kuznetsova A, Lampert C, Ferrari V. Detecting visual relationships using box attention. In: Proceedings of the 2019 International Conference on Computer Vision Workshop. IEEE; 2019. doi:10.1109/ICCVW.2019.00217","chicago":"Kolesnikov, Alexander, Alina Kuznetsova, Christoph Lampert, and Vittorio Ferrari. “Detecting Visual Relationships Using Box Attention.” In Proceedings of the 2019 International Conference on Computer Vision Workshop. IEEE, 2019. https://doi.org/10.1109/ICCVW.2019.00217.","mla":"Kolesnikov, Alexander, et al. “Detecting Visual Relationships Using Box Attention.” Proceedings of the 2019 International Conference on Computer Vision Workshop, 1749–1753, IEEE, 2019, doi:10.1109/ICCVW.2019.00217.","short":"A. Kolesnikov, A. Kuznetsova, C. Lampert, V. Ferrari, in:, Proceedings of the 2019 International Conference on Computer Vision Workshop, IEEE, 2019."},"publication":"Proceedings of the 2019 International Conference on Computer Vision Workshop","article_processing_charge":"No","day":"01","scopus_import":"1","date_updated":"2023-09-08T11:18:37Z","date_created":"2020-04-05T22:00:51Z","author":[{"last_name":"Kolesnikov","first_name":"Alexander","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander"},{"first_name":"Alina","last_name":"Kuznetsova","full_name":"Kuznetsova, Alina"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"},{"first_name":"Vittorio","last_name":"Ferrari","full_name":"Ferrari, Vittorio"}],"department":[{"_id":"ChLa"}],"publisher":"IEEE","publication_status":"published","year":"2019","ec_funded":1,"article_number":"1749-1753","language":[{"iso":"eng"}],"doi":"10.1109/ICCVW.2019.00217","conference":{"name":"ICCVW: International Conference on Computer Vision Workshop","end_date":"2019-10-28","start_date":"2019-10-27","location":"Seoul, South Korea"},"project":[{"call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"isi":1,"quality_controlled":"1","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1807.02136"}],"external_id":{"isi":["000554591601098"],"arxiv":["1807.02136"]},"oa":1,"publication_identifier":{"isbn":["9781728150239"]},"month":"10"},{"file_date_updated":"2020-07-14T12:47:33Z","date_updated":"2023-10-17T12:31:38Z","date_created":"2019-06-20T18:23:03Z","volume":97,"author":[{"last_name":"Bui Thi Mai","first_name":"Phuong","id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87","full_name":"Bui Thi Mai, Phuong"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"publication_status":"published","publisher":"ML Research Press","department":[{"_id":"ChLa"}],"year":"2019","month":"06","language":[{"iso":"eng"}],"conference":{"name":"ICML: International Conference on Machine Learning","location":"Long Beach, CA, United States","start_date":"2019-06-10","end_date":"2019-06-15"},"quality_controlled":"1","oa":1,"abstract":[{"text":"Knowledge distillation, i.e. one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much faster and more reliably if trained with the outputs of another classifier as soft labels, instead of from ground truth data. So far, however, there is no satisfactory theoretical explanation of this phenomenon. In this work, we provide the first insights into the working mechanisms of distillation by studying the special case of linear and deep linear classifiers. Specifically, we prove a generalization bound that establishes fast convergence of the expected risk of a distillation-trained linear classifier. From the bound and its proof we extract three keyfactors that determine the success of distillation: data geometry – geometric properties of the datadistribution, in particular class separation, has an immediate influence on the convergence speed of the risk; optimization bias– gradient descentoptimization finds a very favorable minimum of the distillation objective; and strong monotonicity– the expected risk of the student classifier always decreases when the size of the training set grows.","lang":"eng"}],"type":"conference","file":[{"file_id":"6570","relation":"main_file","checksum":"a66d00e2694d749250f8507f301320ca","date_updated":"2020-07-14T12:47:33Z","date_created":"2019-06-20T18:22:56Z","access_level":"open_access","file_name":"paper.pdf","creator":"bphuong","content_type":"application/pdf","file_size":686432}],"oa_version":"Published Version","ddc":["000"],"status":"public","title":"Towards understanding knowledge distillation","intvolume":" 97","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"6569","day":"13","has_accepted_license":"1","article_processing_charge":"No","scopus_import":"1","date_published":"2019-06-13T00:00:00Z","page":"5142-5151","publication":"Proceedings of the 36th International Conference on Machine Learning","citation":{"ista":"Phuong M, Lampert C. 2019. Towards understanding knowledge distillation. Proceedings of the 36th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 97, 5142–5151.","ieee":"M. Phuong and C. Lampert, “Towards understanding knowledge distillation,” in Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, United States, 2019, vol. 97, pp. 5142–5151.","apa":"Phuong, M., & Lampert, C. (2019). Towards understanding knowledge distillation. In Proceedings of the 36th International Conference on Machine Learning (Vol. 97, pp. 5142–5151). Long Beach, CA, United States: ML Research Press.","ama":"Phuong M, Lampert C. Towards understanding knowledge distillation. In: Proceedings of the 36th International Conference on Machine Learning. Vol 97. ML Research Press; 2019:5142-5151.","chicago":"Phuong, Mary, and Christoph Lampert. “Towards Understanding Knowledge Distillation.” In Proceedings of the 36th International Conference on Machine Learning, 97:5142–51. ML Research Press, 2019.","mla":"Phuong, Mary, and Christoph Lampert. “Towards Understanding Knowledge Distillation.” Proceedings of the 36th International Conference on Machine Learning, vol. 97, ML Research Press, 2019, pp. 5142–51.","short":"M. Phuong, C. Lampert, in:, Proceedings of the 36th International Conference on Machine Learning, ML Research Press, 2019, pp. 5142–5151."}},{"conference":{"name":"ICML: International Conference on Machine Learning","location":"Long Beach, CA, USA","start_date":"2019-06-10","end_date":"2919-06-15"},"language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1901.10310"}],"oa":1,"external_id":{"arxiv":["1901.10310"]},"project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"},{"name":"International IST Doctoral Program","call_identifier":"H2020","_id":"2564DBCA-B435-11E9-9278-68D0E5697425","grant_number":"665385"}],"quality_controlled":"1","month":"06","related_material":{"record":[{"status":"public","relation":"dissertation_contains","id":"10799"}]},"author":[{"full_name":"Konstantinov, Nikola H","last_name":"Konstantinov","first_name":"Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"volume":97,"date_updated":"2023-10-17T12:31:55Z","date_created":"2019-06-27T14:18:23Z","year":"2019","publisher":"ML Research Press","department":[{"_id":"ChLa"}],"publication_status":"published","ec_funded":1,"date_published":"2019-06-01T00:00:00Z","citation":{"short":"N.H. Konstantinov, C. Lampert, in:, Proceedings of the 36th International Conference on Machine Learning, ML Research Press, 2019, pp. 3488–3498.","mla":"Konstantinov, Nikola H., and Christoph Lampert. “Robust Learning from Untrusted Sources.” Proceedings of the 36th International Conference on Machine Learning, vol. 97, ML Research Press, 2019, pp. 3488–98.","chicago":"Konstantinov, Nikola H, and Christoph Lampert. “Robust Learning from Untrusted Sources.” In Proceedings of the 36th International Conference on Machine Learning, 97:3488–98. ML Research Press, 2019.","ama":"Konstantinov NH, Lampert C. Robust learning from untrusted sources. In: Proceedings of the 36th International Conference on Machine Learning. Vol 97. ML Research Press; 2019:3488-3498.","apa":"Konstantinov, N. H., & Lampert, C. (2019). Robust learning from untrusted sources. In Proceedings of the 36th International Conference on Machine Learning (Vol. 97, pp. 3488–3498). Long Beach, CA, USA: ML Research Press.","ieee":"N. H. Konstantinov and C. Lampert, “Robust learning from untrusted sources,” in Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA, 2019, vol. 97, pp. 3488–3498.","ista":"Konstantinov NH, Lampert C. 2019. Robust learning from untrusted sources. Proceedings of the 36th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 97, 3488–3498."},"publication":"Proceedings of the 36th International Conference on Machine Learning","page":"3488-3498","article_processing_charge":"No","day":"01","scopus_import":"1","oa_version":"Preprint","_id":"6590","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","intvolume":" 97","title":"Robust learning from untrusted sources","status":"public","abstract":[{"text":"Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality of these sources is not always guaranteed. As additional complications, the data might be stored in a distributed way, or might even have to remain private. In this work, we address the question of how to learn robustly in such scenarios. Studying the problem through the lens of statistical learning theory, we derive a procedure that allows for learning from all available sources, yet automatically suppresses irrelevant or corrupted data. We show by extensive experiments that our method provides significant improvements over alternative approaches from robust statistics and distributed optimization. ","lang":"eng"}],"type":"conference"},{"doi":"10.1007/978-3-030-12939-2_18","conference":{"start_date":"2018-10-09","location":"Stuttgart, Germany","end_date":"2018-10-12","name":"GCPR: Conference on Pattern Recognition"},"language":[{"iso":"eng"}],"oa":1,"external_id":{"arxiv":["1804.04171"]},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1804.04171"}],"project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7"}],"quality_controlled":"1","publication_identifier":{"issn":["0302-9743"],"isbn":["9783030129385","9783030129392"],"eissn":["1611-3349"]},"month":"02","related_material":{"record":[{"id":"6944","status":"public","relation":"later_version"}]},"author":[{"last_name":"Sun","first_name":"Rémy","full_name":"Sun, Rémy"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"volume":11269,"date_created":"2019-05-24T09:48:36Z","date_updated":"2024-02-22T14:57:29Z","year":"2019","publisher":"Springer Nature","department":[{"_id":"ChLa"}],"publication_status":"published","ec_funded":1,"date_published":"2019-02-14T00:00:00Z","citation":{"ista":"Sun R, Lampert C. 2019. KS(conf): A light-weight test if a ConvNet operates outside of Its specifications. GCPR: Conference on Pattern Recognition, LNCS, vol. 11269, 244–259.","apa":"Sun, R., & Lampert, C. (2019). KS(conf): A light-weight test if a ConvNet operates outside of Its specifications (Vol. 11269, pp. 244–259). Presented at the GCPR: Conference on Pattern Recognition, Stuttgart, Germany: Springer Nature. https://doi.org/10.1007/978-3-030-12939-2_18","ieee":"R. Sun and C. Lampert, “KS(conf): A light-weight test if a ConvNet operates outside of Its specifications,” presented at the GCPR: Conference on Pattern Recognition, Stuttgart, Germany, 2019, vol. 11269, pp. 244–259.","ama":"Sun R, Lampert C. KS(conf): A light-weight test if a ConvNet operates outside of Its specifications. In: Vol 11269. Springer Nature; 2019:244-259. doi:10.1007/978-3-030-12939-2_18","chicago":"Sun, Rémy, and Christoph Lampert. “KS(Conf): A Light-Weight Test If a ConvNet Operates Outside of Its Specifications,” 11269:244–59. Springer Nature, 2019. https://doi.org/10.1007/978-3-030-12939-2_18.","mla":"Sun, Rémy, and Christoph Lampert. KS(Conf): A Light-Weight Test If a ConvNet Operates Outside of Its Specifications. Vol. 11269, Springer Nature, 2019, pp. 244–59, doi:10.1007/978-3-030-12939-2_18.","short":"R. Sun, C. Lampert, in:, Springer Nature, 2019, pp. 244–259."},"page":"244-259","article_processing_charge":"No","day":"14","scopus_import":"1","oa_version":"Preprint","_id":"6482","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","intvolume":" 11269","title":"KS(conf): A light-weight test if a ConvNet operates outside of Its specifications","status":"public","abstract":[{"lang":"eng","text":"Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under the specific conditions, in particular data distributions, that they were trained for. Surprisingly, none of the currently used deep network architectures have a built-in functionality that could detect if a network operates on data from a distribution it was not trained for, such that potentially a warning to the human users could be triggered. In this work, we describe KS(conf), a procedure for detecting such outside of specifications (out-of-specs) operation, based on statistical testing of the network outputs. We show by extensive experiments using the ImageNet, AwA2 and DAVIS datasets on a variety of ConvNets architectures that KS(conf) reliably detects out-of-specs situations. It furthermore has a number of properties that make it a promising candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with all networks, including pretrained ones, and requires no a priori knowledge of how the data distribution could change. "}],"type":"conference","alternative_title":["LNCS"]},{"abstract":[{"text":"The most common assumption made in statistical learning theory is the assumption of the independent and identically distributed (i.i.d.) data. While being very convenient mathematically, it is often very clearly violated in practice. This disparity between the machine learning theory and applications underlies a growing demand in the development of algorithms that learn from dependent data and theory that can provide generalization guarantees similar to the independent situations. This thesis is dedicated to two variants of dependencies that can arise in practice. One is a dependence on the level of samples in a single learning task. Another dependency type arises in the multi-task setting when the tasks are dependent on each other even though the data for them can be i.i.d. In both cases we model the data (samples or tasks) as stochastic processes and introduce new algorithms for both settings that take into account and exploit the resulting dependencies. We prove the theoretical guarantees on the performance of the introduced algorithms under different evaluation criteria and, in addition, we compliment the theoretical study by the empirical one, where we evaluate some of the algorithms on two real world datasets to highlight their practical applicability.","lang":"eng"}],"alternative_title":["ISTA Thesis"],"type":"dissertation","oa_version":"Published Version","file":[{"file_name":"2018_Thesis_Zimin.pdf","access_level":"open_access","file_size":1036137,"content_type":"application/pdf","creator":"dernst","relation":"main_file","file_id":"6253","date_created":"2019-04-09T07:32:47Z","date_updated":"2020-07-14T12:47:40Z","checksum":"e849dd40a915e4d6c5572b51b517f098"},{"access_level":"closed","file_name":"2018_Thesis_Zimin_Source.zip","creator":"dernst","content_type":"application/zip","file_size":637490,"file_id":"6254","relation":"source_file","checksum":"da092153cec55c97461bd53c45c5d139","date_created":"2019-04-09T07:32:47Z","date_updated":"2020-07-14T12:47:40Z"}],"pubrep_id":"1048","status":"public","title":"Learning from dependent data","ddc":["004","519"],"_id":"68","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","article_processing_charge":"No","has_accepted_license":"1","day":"01","date_published":"2018-09-01T00:00:00Z","page":"92","citation":{"ama":"Zimin A. Learning from dependent data. 2018. doi:10.15479/AT:ISTA:TH1048","ista":"Zimin A. 2018. Learning from dependent data. Institute of Science and Technology Austria.","apa":"Zimin, A. (2018). Learning from dependent data. Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:TH1048","ieee":"A. Zimin, “Learning from dependent data,” Institute of Science and Technology Austria, 2018.","mla":"Zimin, Alexander. Learning from Dependent Data. Institute of Science and Technology Austria, 2018, doi:10.15479/AT:ISTA:TH1048.","short":"A. Zimin, Learning from Dependent Data, Institute of Science and Technology Austria, 2018.","chicago":"Zimin, Alexander. “Learning from Dependent Data.” Institute of Science and Technology Austria, 2018. https://doi.org/10.15479/AT:ISTA:TH1048."},"ec_funded":1,"publist_id":"7986","file_date_updated":"2020-07-14T12:47:40Z","date_updated":"2023-09-07T12:29:07Z","date_created":"2018-12-11T11:44:27Z","author":[{"full_name":"Zimin, Alexander","last_name":"Zimin","first_name":"Alexander","id":"37099E9C-F248-11E8-B48F-1D18A9856A87"}],"publisher":"Institute of Science and Technology Austria","department":[{"_id":"ChLa"}],"publication_status":"published","year":"2018","publication_identifier":{"issn":["2663-337X"]},"month":"09","language":[{"iso":"eng"}],"supervisor":[{"full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"degree_awarded":"PhD","doi":"10.15479/AT:ISTA:TH1048","project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"oa":1},{"publication_identifier":{"issn":["2663-337X"]},"month":"05","oa":1,"project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"doi":"10.15479/AT:ISTA:th_1021","language":[{"iso":"eng"}],"degree_awarded":"PhD","supervisor":[{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"ec_funded":1,"publist_id":"7718","file_date_updated":"2020-07-14T12:45:22Z","acknowledgement":"I also gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research.","year":"2018","publisher":"Institute of Science and Technology Austria","department":[{"_id":"ChLa"}],"publication_status":"published","author":[{"full_name":"Kolesnikov, Alexander","first_name":"Alexander","last_name":"Kolesnikov","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87"}],"date_updated":"2023-09-07T12:51:46Z","date_created":"2018-12-11T11:45:09Z","has_accepted_license":"1","article_processing_charge":"No","day":"25","citation":{"chicago":"Kolesnikov, Alexander. “Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images.” Institute of Science and Technology Austria, 2018. https://doi.org/10.15479/AT:ISTA:th_1021.","short":"A. Kolesnikov, Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images, Institute of Science and Technology Austria, 2018.","mla":"Kolesnikov, Alexander. Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images. Institute of Science and Technology Austria, 2018, doi:10.15479/AT:ISTA:th_1021.","apa":"Kolesnikov, A. (2018). Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images. Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:th_1021","ieee":"A. Kolesnikov, “Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images,” Institute of Science and Technology Austria, 2018.","ista":"Kolesnikov A. 2018. Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images. Institute of Science and Technology Austria.","ama":"Kolesnikov A. Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images. 2018. doi:10.15479/AT:ISTA:th_1021"},"page":"113","date_published":"2018-05-25T00:00:00Z","type":"dissertation","alternative_title":["ISTA Thesis"],"abstract":[{"text":"Modern computer vision systems heavily rely on statistical machine learning models, which typically require large amounts of labeled data to be learned reliably. Moreover, very recently computer vision research widely adopted techniques for representation learning, which further increase the demand for labeled data. However, for many important practical problems there is relatively small amount of labeled data available, so it is problematic to leverage full potential of the representation learning methods. One way to overcome this obstacle is to invest substantial resources into producing large labelled datasets. Unfortunately, this can be prohibitively expensive in practice. In this thesis we focus on the alternative way of tackling the aforementioned issue. We concentrate on methods, which make use of weakly-labeled or even unlabeled data. Specifically, the first half of the thesis is dedicated to the semantic image segmentation task. We develop a technique, which achieves competitive segmentation performance and only requires annotations in a form of global image-level labels instead of dense segmentation masks. Subsequently, we present a new methodology, which further improves segmentation performance by leveraging tiny additional feedback from a human annotator. By using our methods practitioners can greatly reduce the amount of data annotation effort, which is required to learn modern image segmentation models. In the second half of the thesis we focus on methods for learning from unlabeled visual data. We study a family of autoregressive models for modeling structure of natural images and discuss potential applications of these models. Moreover, we conduct in-depth study of one of these applications, where we develop the state-of-the-art model for the probabilistic image colorization task.","lang":"eng"}],"_id":"197","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","status":"public","ddc":["004"],"title":"Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images","pubrep_id":"1021","file":[{"checksum":"bc678e02468d8ebc39dc7267dfb0a1c4","date_created":"2018-12-12T10:14:57Z","date_updated":"2020-07-14T12:45:22Z","file_id":"5113","relation":"main_file","creator":"system","content_type":"application/pdf","file_size":12918758,"access_level":"open_access","file_name":"IST-2018-1021-v1+1_thesis-unsigned-pdfa.pdf"},{"creator":"dernst","file_size":55973760,"content_type":"application/zip","access_level":"closed","file_name":"2018_Thesis_Kolesnikov_source.zip","checksum":"bc66973b086da5a043f1162dcfb1fde4","date_updated":"2020-07-14T12:45:22Z","date_created":"2019-04-05T09:34:49Z","file_id":"6225","relation":"source_file"}],"oa_version":"Published Version"},{"month":"03","doi":"10.1534/genetics.117.300638","language":[{"iso":"eng"}],"external_id":{"isi":["000426219600025"]},"oa":1,"main_file_link":[{"url":"https://www.biorxiv.org/content/10.1101/205484v1","open_access":"1"}],"isi":1,"quality_controlled":"1","publist_id":"7251","author":[{"full_name":"Ringbauer, Harald","orcid":"0000-0002-4884-9682","id":"417FCFF4-F248-11E8-B48F-1D18A9856A87","last_name":"Ringbauer","first_name":"Harald"},{"full_name":"Kolesnikov, Alexander","first_name":"Alexander","last_name":"Kolesnikov","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Field","first_name":"David","full_name":"Field, David"},{"full_name":"Barton, Nicholas H","orcid":"0000-0002-8548-5240","id":"4880FE40-F248-11E8-B48F-1D18A9856A87","last_name":"Barton","first_name":"Nicholas H"}],"related_material":{"record":[{"id":"200","status":"public","relation":"dissertation_contains"}]},"date_created":"2018-12-11T11:47:12Z","date_updated":"2023-09-11T13:42:38Z","volume":208,"year":"2018","publication_status":"published","publisher":"Genetics Society of America","department":[{"_id":"NiBa"},{"_id":"ChLa"}],"day":"01","article_processing_charge":"No","scopus_import":"1","date_published":"2018-03-01T00:00:00Z","publication":"Genetics","citation":{"ieee":"H. Ringbauer, A. Kolesnikov, D. Field, and N. H. Barton, “Estimating barriers to gene flow from distorted isolation-by-distance patterns,” Genetics, vol. 208, no. 3. Genetics Society of America, pp. 1231–1245, 2018.","apa":"Ringbauer, H., Kolesnikov, A., Field, D., & Barton, N. H. (2018). Estimating barriers to gene flow from distorted isolation-by-distance patterns. Genetics. Genetics Society of America. https://doi.org/10.1534/genetics.117.300638","ista":"Ringbauer H, Kolesnikov A, Field D, Barton NH. 2018. Estimating barriers to gene flow from distorted isolation-by-distance patterns. Genetics. 208(3), 1231–1245.","ama":"Ringbauer H, Kolesnikov A, Field D, Barton NH. Estimating barriers to gene flow from distorted isolation-by-distance patterns. Genetics. 2018;208(3):1231-1245. doi:10.1534/genetics.117.300638","chicago":"Ringbauer, Harald, Alexander Kolesnikov, David Field, and Nicholas H Barton. “Estimating Barriers to Gene Flow from Distorted Isolation-by-Distance Patterns.” Genetics. Genetics Society of America, 2018. https://doi.org/10.1534/genetics.117.300638.","short":"H. Ringbauer, A. Kolesnikov, D. Field, N.H. Barton, Genetics 208 (2018) 1231–1245.","mla":"Ringbauer, Harald, et al. “Estimating Barriers to Gene Flow from Distorted Isolation-by-Distance Patterns.” Genetics, vol. 208, no. 3, Genetics Society of America, 2018, pp. 1231–45, doi:10.1534/genetics.117.300638."},"page":"1231-1245","abstract":[{"text":"In continuous populations with local migration, nearby pairs of individuals have on average more similar genotypes\r\nthan geographically well separated pairs. A barrier to gene flow distorts this classical pattern of isolation by distance. Genetic similarity is decreased for sample pairs on different sides of the barrier and increased for pairs on the same side near the barrier. Here, we introduce an inference scheme that utilizes this signal to detect and estimate the strength of a linear barrier to gene flow in two-dimensions. We use a diffusion approximation to model the effects of a barrier on the geographical spread of ancestry backwards in time. This approach allows us to calculate the chance of recent coalescence and probability of identity by descent. We introduce an inference scheme that fits these theoretical results to the geographical covariance structure of bialleleic genetic markers. It can estimate the strength of the barrier as well as several demographic parameters. We investigate the power of our inference scheme to detect barriers by applying it to a wide range of simulated data. We also showcase an example application to a Antirrhinum majus (snapdragon) flower color hybrid zone, where we do not detect any signal of a strong genome wide barrier to gene flow.","lang":"eng"}],"issue":"3","type":"journal_article","oa_version":"Preprint","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","_id":"563","status":"public","title":"Estimating barriers to gene flow from distorted isolation-by-distance patterns","intvolume":" 208"},{"external_id":{"isi":["000428901200001"]},"oa":1,"quality_controlled":"1","isi":1,"doi":"10.1109/TPAMI.2018.2804998","language":[{"iso":"eng"}],"month":"05","year":"2018","publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"IEEE","author":[{"last_name":"Darrell","first_name":"Trevor","full_name":"Darrell, Trevor"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert"},{"full_name":"Sebe, Nico","last_name":"Sebe","first_name":"Nico"},{"first_name":"Ying","last_name":"Wu","full_name":"Wu, Ying"},{"full_name":"Yan, Yan","first_name":"Yan","last_name":"Yan"}],"date_created":"2018-12-11T11:45:48Z","date_updated":"2023-09-11T14:07:54Z","volume":40,"file_date_updated":"2020-07-14T12:46:03Z","publist_id":"7544","publication":"IEEE Transactions on Pattern Analysis and Machine Intelligence","citation":{"short":"T. Darrell, C. Lampert, N. Sebe, Y. Wu, Y. Yan, IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (2018) 1029–1031.","mla":"Darrell, Trevor, et al. “Guest Editors’ Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 5, IEEE, 2018, pp. 1029–31, doi:10.1109/TPAMI.2018.2804998.","chicago":"Darrell, Trevor, Christoph Lampert, Nico Sebe, Ying Wu, and Yan Yan. “Guest Editors’ Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis.” IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE, 2018. https://doi.org/10.1109/TPAMI.2018.2804998.","ama":"Darrell T, Lampert C, Sebe N, Wu Y, Yan Y. Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018;40(5):1029-1031. doi:10.1109/TPAMI.2018.2804998","ieee":"T. Darrell, C. Lampert, N. Sebe, Y. Wu, and Y. Yan, “Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 5. IEEE, pp. 1029–1031, 2018.","apa":"Darrell, T., Lampert, C., Sebe, N., Wu, Y., & Yan, Y. (2018). Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE. https://doi.org/10.1109/TPAMI.2018.2804998","ista":"Darrell T, Lampert C, Sebe N, Wu Y, Yan Y. 2018. Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 40(5), 1029–1031."},"article_type":"original","page":"1029 - 1031","date_published":"2018-05-01T00:00:00Z","scopus_import":"1","day":"01","has_accepted_license":"1","article_processing_charge":"No","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","_id":"321","status":"public","ddc":["000"],"title":"Guest editors' introduction to the special section on learning with Shared information for computer vision and multimedia analysis","intvolume":" 40","oa_version":"Published Version","file":[{"date_updated":"2020-07-14T12:46:03Z","date_created":"2020-05-14T12:50:48Z","checksum":"b19c75da06faf3291a3ca47dfa50ef63","relation":"main_file","file_id":"7835","file_size":141724,"content_type":"application/pdf","creator":"dernst","file_name":"2018_IEEE_Darrell.pdf","access_level":"open_access"}],"type":"journal_article","abstract":[{"lang":"eng","text":"The twelve papers in this special section focus on learning systems with shared information for computer vision and multimedia communication analysis. In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes containing a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with shared information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different levels of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems."}],"issue":"5"},{"type":"conference","abstract":[{"lang":"eng","text":"We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider two actions: box verification [34], where the annotator verifies a box generated by an object detector, and manual box drawing. We explore two kinds of agents, one based on predicting the probability that a box will be positively verified, and the other based on reinforcement learning. We demonstrate that (1) our agents are able to learn efficient annotation strategies in several scenarios, automatically adapting to the image difficulty, the desired quality of the boxes, and the detector strength; (2) in all scenarios the resulting annotation dialogs speed up annotation compared to manual box drawing alone and box verification alone, while also outperforming any fixed combination of verification and drawing in most scenarios; (3) in a realistic scenario where the detector is iteratively re-trained, our agents evolve a series of strategies that reflect the shifting trade-off between verification and drawing as the detector grows stronger."}],"title":"Learning intelligent dialogs for bounding box annotation","status":"public","_id":"10882","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","oa_version":"Preprint","scopus_import":"1","day":"17","article_processing_charge":"No","page":"9175-9184","publication":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","citation":{"chicago":"Uijlings, Jasper, Ksenia Konyushkova, Christoph Lampert, and Vittorio Ferrari. “Learning Intelligent Dialogs for Bounding Box Annotation.” In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9175–84. IEEE, 2018. https://doi.org/10.1109/cvpr.2018.00956.","short":"J. Uijlings, K. Konyushkova, C. Lampert, V. Ferrari, in:, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018, pp. 9175–9184.","mla":"Uijlings, Jasper, et al. “Learning Intelligent Dialogs for Bounding Box Annotation.” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018, pp. 9175–84, doi:10.1109/cvpr.2018.00956.","ieee":"J. Uijlings, K. Konyushkova, C. Lampert, and V. Ferrari, “Learning intelligent dialogs for bounding box annotation,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, United States, 2018, pp. 9175–9184.","apa":"Uijlings, J., Konyushkova, K., Lampert, C., & Ferrari, V. (2018). Learning intelligent dialogs for bounding box annotation. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9175–9184). Salt Lake City, UT, United States: IEEE. https://doi.org/10.1109/cvpr.2018.00956","ista":"Uijlings J, Konyushkova K, Lampert C, Ferrari V. 2018. Learning intelligent dialogs for bounding box annotation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVF: Conference on Computer Vision and Pattern Recognition, 9175–9184.","ama":"Uijlings J, Konyushkova K, Lampert C, Ferrari V. Learning intelligent dialogs for bounding box annotation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE; 2018:9175-9184. doi:10.1109/cvpr.2018.00956"},"date_published":"2018-12-17T00:00:00Z","publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"IEEE","year":"2018","date_created":"2022-03-18T12:45:09Z","date_updated":"2023-09-19T15:11:49Z","author":[{"full_name":"Uijlings, Jasper","first_name":"Jasper","last_name":"Uijlings"},{"last_name":"Konyushkova","first_name":"Ksenia","full_name":"Konyushkova, Ksenia"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert"},{"first_name":"Vittorio","last_name":"Ferrari","full_name":"Ferrari, Vittorio"}],"month":"12","publication_identifier":{"eissn":["2575-7075"],"isbn":["9781538664209"]},"quality_controlled":"1","isi":1,"oa":1,"external_id":{"arxiv":["1712.08087"],"isi":["000457843609036"]},"main_file_link":[{"url":" https://doi.org/10.48550/arXiv.1712.08087","open_access":"1"}],"language":[{"iso":"eng"}],"conference":{"name":"CVF: Conference on Computer Vision and Pattern Recognition","location":"Salt Lake City, UT, United States","start_date":"2018-06-18","end_date":"2018-06-23"},"doi":"10.1109/cvpr.2018.00956"},{"ec_funded":1,"author":[{"full_name":"Sahoo, Subham","first_name":"Subham","last_name":"Sahoo"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"},{"full_name":"Martius, Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","first_name":"Georg S","last_name":"Martius"}],"related_material":{"link":[{"url":"https://ist.ac.at/en/news/first-machine-learning-method-capable-of-accurate-extrapolation/","relation":"press_release","description":"News on IST Homepage"}]},"date_created":"2019-02-14T15:21:07Z","date_updated":"2023-10-17T09:50:53Z","volume":80,"year":"2018","publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"ML Research Press","month":"02","conference":{"location":"Stockholm, Sweden","start_date":"2018-07-10","end_date":"2018-07-15","name":"ICML: International Conference on Machine Learning"},"language":[{"iso":"eng"}],"oa":1,"main_file_link":[{"url":"https://arxiv.org/abs/1806.07259","open_access":"1"}],"external_id":{"arxiv":["1806.07259"],"isi":["000683379204058"]},"isi":1,"quality_controlled":"1","project":[{"grant_number":"291734","_id":"25681D80-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"International IST Postdoc Fellowship Programme"}],"abstract":[{"lang":"eng","text":"We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task."}],"type":"conference","oa_version":"Preprint","_id":"6012","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","title":"Learning equations for extrapolation and control","intvolume":" 80","day":"01","article_processing_charge":"No","scopus_import":"1","date_published":"2018-02-01T00:00:00Z","publication":"Proceedings of the 35th International Conference on Machine Learning","citation":{"ista":"Sahoo S, Lampert C, Martius GS. 2018. Learning equations for extrapolation and control. Proceedings of the 35th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 80, 4442–4450.","ieee":"S. Sahoo, C. Lampert, and G. S. Martius, “Learning equations for extrapolation and control,” in Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, 2018, vol. 80, pp. 4442–4450.","apa":"Sahoo, S., Lampert, C., & Martius, G. S. (2018). Learning equations for extrapolation and control. In Proceedings of the 35th International Conference on Machine Learning (Vol. 80, pp. 4442–4450). Stockholm, Sweden: ML Research Press.","ama":"Sahoo S, Lampert C, Martius GS. Learning equations for extrapolation and control. In: Proceedings of the 35th International Conference on Machine Learning. Vol 80. ML Research Press; 2018:4442-4450.","chicago":"Sahoo, Subham, Christoph Lampert, and Georg S Martius. “Learning Equations for Extrapolation and Control.” In Proceedings of the 35th International Conference on Machine Learning, 80:4442–50. ML Research Press, 2018.","mla":"Sahoo, Subham, et al. “Learning Equations for Extrapolation and Control.” Proceedings of the 35th International Conference on Machine Learning, vol. 80, ML Research Press, 2018, pp. 4442–50.","short":"S. Sahoo, C. Lampert, G.S. Martius, in:, Proceedings of the 35th International Conference on Machine Learning, ML Research Press, 2018, pp. 4442–4450."},"page":"4442-4450"},{"page":"2815-2824","publication":"Proceedings of the 35 th International Conference on Machine Learning","citation":{"mla":"Kuzborskij, Ilja, and Christoph Lampert. “Data-Dependent Stability of Stochastic Gradient Descent.” Proceedings of the 35 Th International Conference on Machine Learning, vol. 80, ML Research Press, 2018, pp. 2815–24.","short":"I. Kuzborskij, C. Lampert, in:, Proceedings of the 35 Th International Conference on Machine Learning, ML Research Press, 2018, pp. 2815–2824.","chicago":"Kuzborskij, Ilja, and Christoph Lampert. “Data-Dependent Stability of Stochastic Gradient Descent.” In Proceedings of the 35 Th International Conference on Machine Learning, 80:2815–24. ML Research Press, 2018.","ama":"Kuzborskij I, Lampert C. Data-dependent stability of stochastic gradient descent. In: Proceedings of the 35 Th International Conference on Machine Learning. Vol 80. ML Research Press; 2018:2815-2824.","ista":"Kuzborskij I, Lampert C. 2018. Data-dependent stability of stochastic gradient descent. Proceedings of the 35 th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 80, 2815–2824.","ieee":"I. Kuzborskij and C. Lampert, “Data-dependent stability of stochastic gradient descent,” in Proceedings of the 35 th International Conference on Machine Learning, Stockholm, Sweden, 2018, vol. 80, pp. 2815–2824.","apa":"Kuzborskij, I., & Lampert, C. (2018). Data-dependent stability of stochastic gradient descent. In Proceedings of the 35 th International Conference on Machine Learning (Vol. 80, pp. 2815–2824). Stockholm, Sweden: ML Research Press."},"date_published":"2018-02-01T00:00:00Z","scopus_import":"1","day":"01","article_processing_charge":"No","title":"Data-dependent stability of stochastic gradient descent","status":"public","intvolume":" 80","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"6011","oa_version":"Preprint","type":"conference","abstract":[{"text":"We establish a data-dependent notion of algorithmic stability for Stochastic Gradient Descent (SGD), and employ it to develop novel generalization bounds. This is in contrast to previous distribution-free algorithmic stability results for SGD which depend on the worst-case constants. By virtue of the data-dependent argument, our bounds provide new insights into learning with SGD on convex and non-convex problems. In the convex case, we show that the bound on the generalization error depends on the risk at the initialization point. In the non-convex case, we prove that the expected curvature of the objective function around the initialization point has crucial influence on the generalization error. In both cases, our results suggest a simple data-driven strategy to stabilize SGD by pre-screening its initialization. As a corollary, our results allow us to show optimistic generalization bounds that exhibit fast convergence rates for SGD subject to a vanishing empirical risk and low noise of stochastic gradient. ","lang":"eng"}],"isi":1,"quality_controlled":"1","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7"}],"main_file_link":[{"url":"https://arxiv.org/abs/1703.01678","open_access":"1"}],"external_id":{"arxiv":["1703.01678"],"isi":["000683379202095"]},"oa":1,"language":[{"iso":"eng"}],"conference":{"end_date":"2018-07-15","start_date":"2018-07-10","location":"Stockholm, Sweden","name":"ICML: International Conference on Machine Learning"},"month":"02","publication_status":"published","department":[{"_id":"ChLa"}],"publisher":"ML Research Press","year":"2018","date_updated":"2023-10-17T09:51:13Z","date_created":"2019-02-14T14:51:57Z","volume":80,"author":[{"full_name":"Kuzborskij, Ilja","last_name":"Kuzborskij","first_name":"Ilja"},{"full_name":"Lampert, Christoph","first_name":"Christoph","last_name":"Lampert","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"ec_funded":1},{"conference":{"end_date":"2018-12-08","location":"Montreal, Canada","start_date":"2018-12-02","name":"NeurIPS: Conference on Neural Information Processing Systems"},"language":[{"iso":"eng"}],"oa":1,"external_id":{"isi":["000461852000047"],"arxiv":["1809.10505"]},"main_file_link":[{"url":"https://arxiv.org/abs/1809.10505","open_access":"1"}],"quality_controlled":"1","isi":1,"project":[{"call_identifier":"H2020","name":"International IST Doctoral Program","grant_number":"665385","_id":"2564DBCA-B435-11E9-9278-68D0E5697425"}],"month":"12","author":[{"id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0003-3650-940X","first_name":"Dan-Adrian","last_name":"Alistarh","full_name":"Alistarh, Dan-Adrian"},{"full_name":"Hoefler, Torsten","first_name":"Torsten","last_name":"Hoefler"},{"first_name":"Mikael","last_name":"Johansson","full_name":"Johansson, Mikael"},{"id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87","first_name":"Nikola H","last_name":"Konstantinov","full_name":"Konstantinov, Nikola H"},{"last_name":"Khirirat","first_name":"Sarit","full_name":"Khirirat, Sarit"},{"full_name":"Renggli, Cedric","last_name":"Renggli","first_name":"Cedric"}],"date_created":"2019-06-27T09:32:55Z","date_updated":"2023-10-17T11:47:20Z","volume":"Volume 2018","year":"2018","publication_status":"published","publisher":"Neural Information Processing Systems Foundation","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"ec_funded":1,"date_published":"2018-12-01T00:00:00Z","publication":"Advances in Neural Information Processing Systems 31","citation":{"ista":"Alistarh D-A, Hoefler T, Johansson M, Konstantinov NH, Khirirat S, Renggli C. 2018. The convergence of sparsified gradient methods. Advances in Neural Information Processing Systems 31. NeurIPS: Conference on Neural Information Processing Systems vol. Volume 2018, 5973–5983.","apa":"Alistarh, D.-A., Hoefler, T., Johansson, M., Konstantinov, N. H., Khirirat, S., & Renggli, C. (2018). The convergence of sparsified gradient methods. In Advances in Neural Information Processing Systems 31 (Vol. Volume 2018, pp. 5973–5983). Montreal, Canada: Neural Information Processing Systems Foundation.","ieee":"D.-A. Alistarh, T. Hoefler, M. Johansson, N. H. Konstantinov, S. Khirirat, and C. Renggli, “The convergence of sparsified gradient methods,” in Advances in Neural Information Processing Systems 31, Montreal, Canada, 2018, vol. Volume 2018, pp. 5973–5983.","ama":"Alistarh D-A, Hoefler T, Johansson M, Konstantinov NH, Khirirat S, Renggli C. The convergence of sparsified gradient methods. In: Advances in Neural Information Processing Systems 31. Vol Volume 2018. Neural Information Processing Systems Foundation; 2018:5973-5983.","chicago":"Alistarh, Dan-Adrian, Torsten Hoefler, Mikael Johansson, Nikola H Konstantinov, Sarit Khirirat, and Cedric Renggli. “The Convergence of Sparsified Gradient Methods.” In Advances in Neural Information Processing Systems 31, Volume 2018:5973–83. Neural Information Processing Systems Foundation, 2018.","mla":"Alistarh, Dan-Adrian, et al. “The Convergence of Sparsified Gradient Methods.” Advances in Neural Information Processing Systems 31, vol. Volume 2018, Neural Information Processing Systems Foundation, 2018, pp. 5973–83.","short":"D.-A. Alistarh, T. Hoefler, M. Johansson, N.H. Konstantinov, S. Khirirat, C. Renggli, in:, Advances in Neural Information Processing Systems 31, Neural Information Processing Systems Foundation, 2018, pp. 5973–5983."},"page":"5973-5983","day":"01","article_processing_charge":"No","scopus_import":"1","oa_version":"Preprint","_id":"6589","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","title":"The convergence of sparsified gradient methods","status":"public","abstract":[{"text":"Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization, large-batch methods, and gradient sparsification, have been proposed. To date, gradient sparsification methods--where each node sorts gradients by magnitude, and only communicates a subset of the components, accumulating the rest locally--are known to yield some of the largest practical gains. Such methods can reduce the amount of communication per step by up to \\emph{three orders of magnitude}, while preserving model accuracy. Yet, this family of methods currently has no theoretical justification. This is the question we address in this paper. We prove that, under analytic assumptions, sparsifying gradients by magnitude with local error correction provides convergence guarantees, for both convex and non-convex smooth objectives, for data-parallel SGD. The main insight is that sparsification methods implicitly maintain bounds on the maximum impact of stale updates, thanks to selection by magnitude. Our analysis and empirical validation also reveal that these methods do require analytical conditions to converge well, justifying existing heuristics.","lang":"eng"}],"type":"conference"},{"date_updated":"2024-02-21T13:45:26Z","date_created":"2018-12-12T12:31:39Z","file":[{"creator":"system","file_size":1142543971,"content_type":"application/octet-stream","access_level":"open_access","file_name":"IST-2018-98-v1+1_BBalls_area2_tile2_20x20.mat","checksum":"6808748837b9afbbbabc2a356ca2b88a","date_updated":"2020-07-14T12:47:07Z","date_created":"2018-12-12T13:02:24Z","file_id":"5590","relation":"main_file"},{"creator":"system","file_size":702336,"content_type":"application/pdf","file_name":"IST-2018-98-v1+2_ExperimentStructure.pdf","access_level":"open_access","date_updated":"2020-07-14T12:47:07Z","date_created":"2018-12-12T13:02:25Z","checksum":"d6d6cd07743038fe3a12352983fcf9dd","file_id":"5591","relation":"main_file"},{"checksum":"0c9cfb4dab35bb3dc25a04395600b1c8","date_created":"2018-12-12T13:02:26Z","date_updated":"2020-07-14T12:47:07Z","relation":"main_file","file_id":"5592","content_type":"application/octet-stream","file_size":432,"creator":"system","access_level":"open_access","file_name":"IST-2018-98-v1+3_GoodLocations_area2_20x20.mat"},{"creator":"system","content_type":"text/plain","file_size":986,"file_name":"IST-2018-98-v1+4_README.txt","access_level":"open_access","date_updated":"2020-07-14T12:47:07Z","date_created":"2018-12-12T13:02:26Z","checksum":"2a83b011012e21e934b4596285b1a183","file_id":"5593","relation":"main_file"}],"oa_version":"Published Version","author":[{"first_name":"Stephane","last_name":"Deny","full_name":"Deny, Stephane"},{"full_name":"Marre, Olivier","first_name":"Olivier","last_name":"Marre"},{"full_name":"Botella-Soler, Vicente","first_name":"Vicente","last_name":"Botella-Soler"},{"full_name":"Martius, Georg S","last_name":"Martius","first_name":"Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Tkacik, Gasper","orcid":"0000-0002-6699-1455","id":"3D494DCA-F248-11E8-B48F-1D18A9856A87","last_name":"Tkacik","first_name":"Gasper"}],"related_material":{"record":[{"relation":"used_in_publication","status":"public","id":"292"}]},"ddc":["570"],"title":"Nonlinear decoding of a complex movie from the mammalian retina","status":"public","publisher":"Institute of Science and Technology Austria","department":[{"_id":"ChLa"},{"_id":"GaTk"}],"_id":"5584","year":"2018","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","license":"https://creativecommons.org/publicdomain/zero/1.0/","abstract":[{"lang":"eng","text":"This package contains data for the publication \"Nonlinear decoding of a complex movie from the mammalian retina\" by Deny S. et al, PLOS Comput Biol (2018). \r\n\r\nThe data consists of\r\n(i) 91 spike sorted, isolated rat retinal ganglion cells that pass stability and quality criteria, recorded on the multi-electrode array, in response to the presentation of the complex movie with many randomly moving dark discs. The responses are represented as 648000 x 91 binary matrix, where the first index indicates the timebin of duration 12.5 ms, and the second index the neural identity. The matrix entry is 0/1 if the neuron didn't/did spike in the particular time bin.\r\n(ii) README file and a graphical illustration of the structure of the experiment, specifying how the 648000 timebins are split into epochs where 1, 2, 4, or 10 discs were displayed, and which stimulus segments are exact repeats or unique ball trajectories.\r\n(iii) a 648000 x 400 matrix of luminance traces for each of the 20 x 20 positions (\"sites\") in the movie frame, with time that is locked to the recorded raster. The luminance traces are produced as described in the manuscript by filtering the raw disc movie with a small gaussian spatial kernel. "}],"file_date_updated":"2020-07-14T12:47:07Z","datarep_id":"98","type":"research_data","date_published":"2018-03-29T00:00:00Z","doi":"10.15479/AT:ISTA:98","project":[{"name":"Sensitivity to higher-order statistics in natural scenes","call_identifier":"FWF","_id":"254D1A94-B435-11E9-9278-68D0E5697425","grant_number":"P 25651-N26"}],"tmp":{"short":"CC0 (1.0)","image":"/images/cc_0.png","legal_code_url":"https://creativecommons.org/publicdomain/zero/1.0/legalcode","name":"Creative Commons Public Domain Dedication (CC0 1.0)"},"oa":1,"citation":{"ieee":"S. Deny, O. Marre, V. Botella-Soler, G. S. Martius, and G. Tkačik, “Nonlinear decoding of a complex movie from the mammalian retina.” Institute of Science and Technology Austria, 2018.","apa":"Deny, S., Marre, O., Botella-Soler, V., Martius, G. S., & Tkačik, G. (2018). Nonlinear decoding of a complex movie from the mammalian retina. Institute of Science and Technology Austria. https://doi.org/10.15479/AT:ISTA:98","ista":"Deny S, Marre O, Botella-Soler V, Martius GS, Tkačik G. 2018. Nonlinear decoding of a complex movie from the mammalian retina, Institute of Science and Technology Austria, 10.15479/AT:ISTA:98.","ama":"Deny S, Marre O, Botella-Soler V, Martius GS, Tkačik G. Nonlinear decoding of a complex movie from the mammalian retina. 2018. doi:10.15479/AT:ISTA:98","chicago":"Deny, Stephane, Olivier Marre, Vicente Botella-Soler, Georg S Martius, and Gašper Tkačik. “Nonlinear Decoding of a Complex Movie from the Mammalian Retina.” Institute of Science and Technology Austria, 2018. https://doi.org/10.15479/AT:ISTA:98.","short":"S. Deny, O. Marre, V. Botella-Soler, G.S. Martius, G. Tkačik, (2018).","mla":"Deny, Stephane, et al. Nonlinear Decoding of a Complex Movie from the Mammalian Retina. Institute of Science and Technology Austria, 2018, doi:10.15479/AT:ISTA:98."},"month":"03","day":"29","has_accepted_license":"1","article_processing_charge":"No","keyword":["retina","decoding","regression","neural networks","complex stimulus"]},{"publist_id":"7100","abstract":[{"text":"We present an approach that enables robots to self-organize their sensorimotor behavior from scratch without providing specific information about neither the robot nor its environment. This is achieved by a simple neural control law that increases the consistency between external sensor dynamics and internal neural dynamics of the utterly simple controller. In this way, the embodiment and the agent-environment coupling are the only source of individual development. We show how an anthropomorphic tendon driven arm-shoulder system develops different behaviors depending on that coupling. For instance: Given a bottle half-filled with water, the arm starts to shake it, driven by the physical response of the water. When attaching a brush, the arm can be manipulated into wiping a table, and when connected to a revolvable wheel it finds out how to rotate it. Thus, the robot may be said to discover the affordances of the world. When allowing two (simulated) humanoid robots to interact physically, they engage into a joint behavior development leading to, for instance, spontaneous cooperation. More social effects are observed if the robots can visually perceive each other. Although, as an observer, it is tempting to attribute an apparent intentionality, there is nothing of the kind put in. As a conclusion, we argue that emergent behavior may be much less rooted in explicit intentions, internal motivations, or specific reward systems than is commonly believed.","lang":"eng"}],"type":"conference","article_number":"7846789","oa_version":"None","date_updated":"2021-01-12T08:07:51Z","date_created":"2018-12-11T11:47:43Z","author":[{"last_name":"Der","first_name":"Ralf","full_name":"Der, Ralf"},{"first_name":"Georg S","last_name":"Martius","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","full_name":"Martius, Georg S"}],"department":[{"_id":"ChLa"},{"_id":"GaTk"}],"publisher":"IEEE","title":"Dynamical self consistency leads to behavioral development and emergent social interactions in robots","publication_status":"published","status":"public","_id":"652","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","year":"2017","publication_identifier":{"isbn":["978-150905069-7"]},"day":"07","month":"02","scopus_import":1,"language":[{"iso":"eng"}],"date_published":"2017-02-07T00:00:00Z","doi":"10.1109/DEVLRN.2016.7846789","conference":{"location":"Cergy-Pontoise, France","start_date":"2016-09-19","end_date":"2016-09-22","name":"ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics "},"quality_controlled":"1","citation":{"ama":"Der R, Martius GS. Dynamical self consistency leads to behavioral development and emergent social interactions in robots. In: IEEE; 2017. doi:10.1109/DEVLRN.2016.7846789","ista":"Der R, Martius GS. 2017. Dynamical self consistency leads to behavioral development and emergent social interactions in robots. ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics , 7846789.","apa":"Der, R., & Martius, G. S. (2017). Dynamical self consistency leads to behavioral development and emergent social interactions in robots. Presented at the ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics , Cergy-Pontoise, France: IEEE. https://doi.org/10.1109/DEVLRN.2016.7846789","ieee":"R. Der and G. S. Martius, “Dynamical self consistency leads to behavioral development and emergent social interactions in robots,” presented at the ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics , Cergy-Pontoise, France, 2017.","mla":"Der, Ralf, and Georg S. Martius. Dynamical Self Consistency Leads to Behavioral Development and Emergent Social Interactions in Robots. 7846789, IEEE, 2017, doi:10.1109/DEVLRN.2016.7846789.","short":"R. Der, G.S. Martius, in:, IEEE, 2017.","chicago":"Der, Ralf, and Georg S Martius. “Dynamical Self Consistency Leads to Behavioral Development and Emergent Social Interactions in Robots.” IEEE, 2017. https://doi.org/10.1109/DEVLRN.2016.7846789."}},{"type":"journal_article","abstract":[{"lang":"eng","text":"With the accelerated development of robot technologies, control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of specific objectives for the task at hand. While very successful in many applications, self-organized control schemes seem to be favored in large complex systems with unknown dynamics or which are difficult to model. Reasons are the expected scalability, robustness, and resilience of self-organizing systems. The paper presents a self-learning neurocontroller based on extrinsic differential plasticity introduced recently, applying it to an anthropomorphic musculoskeletal robot arm with attached objects of unknown physical dynamics. The central finding of the paper is the following effect: by the mere feedback through the internal dynamics of the object, the robot is learning to relate each of the objects with a very specific sensorimotor pattern. Specifically, an attached pendulum pilots the arm into a circular motion, a half-filled bottle produces axis oriented shaking behavior, a wheel is getting rotated, and wiping patterns emerge automatically in a table-plus-brush setting. By these object-specific dynamical patterns, the robot may be said to recognize the object's identity, or in other words, it discovers dynamical affordances of objects. Furthermore, when including hand coordinates obtained from a camera, a dedicated hand-eye coordination self-organizes spontaneously. These phenomena are discussed from a specific dynamical system perspective. Central is the dedicated working regime at the border to instability with its potentially infinite reservoir of (limit cycle) attractors "waiting" to be excited. Besides converging toward one of these attractors, variate behavior is also arising from a self-induced attractor morphing driven by the learning rule. We claim that experimental investigations with this anthropomorphic, self-learning robot not only generate interesting and potentially useful behaviors, but may also help to better understand what subjective human muscle feelings are, how they can be rooted in sensorimotor patterns, and how these concepts may feed back on robotics."}],"issue":"MAR","user_id":"2EBD1598-F248-11E8-B48F-1D18A9856A87","_id":"658","ddc":["006"],"status":"public","title":"Self organized behavior generation for musculoskeletal robots","intvolume":" 11","pubrep_id":"903","file":[{"content_type":"application/pdf","file_size":8439566,"creator":"system","file_name":"IST-2017-903-v1+1_fnbot-11-00008.pdf","access_level":"open_access","date_updated":"2020-07-14T12:47:33Z","date_created":"2018-12-12T10:18:49Z","checksum":"b1bc43f96d1df3313c03032c2a46388d","relation":"main_file","file_id":"5371"}],"oa_version":"Published Version","scopus_import":1,"day":"16","article_processing_charge":"Yes","has_accepted_license":"1","publication":"Frontiers in Neurorobotics","citation":{"chicago":"Der, Ralf, and Georg S Martius. “Self Organized Behavior Generation for Musculoskeletal Robots.” Frontiers in Neurorobotics. Frontiers Research Foundation, 2017. https://doi.org/10.3389/fnbot.2017.00008.","short":"R. Der, G.S. Martius, Frontiers in Neurorobotics 11 (2017).","mla":"Der, Ralf, and Georg S. Martius. “Self Organized Behavior Generation for Musculoskeletal Robots.” Frontiers in Neurorobotics, vol. 11, no. MAR, 00008, Frontiers Research Foundation, 2017, doi:10.3389/fnbot.2017.00008.","ieee":"R. Der and G. S. Martius, “Self organized behavior generation for musculoskeletal robots,” Frontiers in Neurorobotics, vol. 11, no. MAR. Frontiers Research Foundation, 2017.","apa":"Der, R., & Martius, G. S. (2017). Self organized behavior generation for musculoskeletal robots. Frontiers in Neurorobotics. Frontiers Research Foundation. https://doi.org/10.3389/fnbot.2017.00008","ista":"Der R, Martius GS. 2017. Self organized behavior generation for musculoskeletal robots. Frontiers in Neurorobotics. 11(MAR), 00008.","ama":"Der R, Martius GS. Self organized behavior generation for musculoskeletal robots. Frontiers in Neurorobotics. 2017;11(MAR). doi:10.3389/fnbot.2017.00008"},"date_published":"2017-03-16T00:00:00Z","article_number":"00008","file_date_updated":"2020-07-14T12:47:33Z","publist_id":"7078","ec_funded":1,"year":"2017","publication_status":"published","publisher":"Frontiers Research Foundation","department":[{"_id":"ChLa"},{"_id":"GaTk"}],"author":[{"last_name":"Der","first_name":"Ralf","full_name":"Der, Ralf"},{"full_name":"Martius, Georg S","last_name":"Martius","first_name":"Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87"}],"date_updated":"2021-01-12T08:08:04Z","date_created":"2018-12-11T11:47:45Z","volume":11,"month":"03","publication_identifier":{"issn":["16625218"]},"oa":1,"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"quality_controlled":"1","project":[{"grant_number":"291734","_id":"25681D80-B435-11E9-9278-68D0E5697425","name":"International IST Postdoc Fellowship Programme","call_identifier":"FP7"}],"doi":"10.3389/fnbot.2017.00008","language":[{"iso":"eng"}]},{"ec_funded":1,"abstract":[{"lang":"eng","text":"In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable feed-forward network and allows for efficient gradient based training. Due to sparsity regularization concise interpretable expressions can be obtained. Often the true underlying source expression is identified."}],"type":"conference","oa_version":"Preprint","date_updated":"2021-01-12T08:09:17Z","date_created":"2019-09-01T22:01:00Z","author":[{"id":"3A276B68-F248-11E8-B48F-1D18A9856A87","last_name":"Martius","first_name":"Georg S","full_name":"Martius, Georg S"},{"last_name":"Lampert","first_name":"Christoph","orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"}],"department":[{"_id":"ChLa"}],"publisher":"International Conference on Learning Representations","status":"public","title":"Extrapolation and learning equations","publication_status":"published","_id":"6841","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","year":"2017","month":"02","day":"21","scopus_import":1,"language":[{"iso":"eng"}],"date_published":"2017-02-21T00:00:00Z","conference":{"start_date":"2017-04-24","location":"Toulon, France","end_date":"2017-04-26","name":"ICLR: International Conference on Learning Representations"},"project":[{"call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036"}],"quality_controlled":"1","citation":{"ieee":"G. S. Martius and C. Lampert, “Extrapolation and learning equations,” in 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, Toulon, France, 2017.","apa":"Martius, G. S., & Lampert, C. (2017). Extrapolation and learning equations. In 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. Toulon, France: International Conference on Learning Representations.","ista":"Martius GS, Lampert C. 2017. Extrapolation and learning equations. 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. ICLR: International Conference on Learning Representations.","ama":"Martius GS, Lampert C. Extrapolation and learning equations. In: 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. International Conference on Learning Representations; 2017.","chicago":"Martius, Georg S, and Christoph Lampert. “Extrapolation and Learning Equations.” In 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. International Conference on Learning Representations, 2017.","short":"G.S. Martius, C. Lampert, in:, 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, International Conference on Learning Representations, 2017.","mla":"Martius, Georg S., and Christoph Lampert. “Extrapolation and Learning Equations.” 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, International Conference on Learning Representations, 2017."},"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1610.02995"}],"external_id":{"arxiv":["1610.02995"]},"oa":1,"publication":"5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings"},{"conference":{"name":"Big Data","start_date":"2017-12-11","location":"Boston, MA, United States","end_date":"2017-12-14"},"doi":"10.1109/BigData.2017.8258375","date_published":"2017-12-01T00:00:00Z","language":[{"iso":"eng"}],"publication":"2017 IEEE International Conference on Big Data","citation":{"ista":"Pielorz J, Prandtstetter M, Straub M, Lampert C. 2017. Optimal geospatial volunteer allocation needs realistic distances. 2017 IEEE International Conference on Big Data. Big Data, 3760–3763.","apa":"Pielorz, J., Prandtstetter, M., Straub, M., & Lampert, C. (2017). Optimal geospatial volunteer allocation needs realistic distances. In 2017 IEEE International Conference on Big Data (pp. 3760–3763). Boston, MA, United States: IEEE. https://doi.org/10.1109/BigData.2017.8258375","ieee":"J. Pielorz, M. Prandtstetter, M. Straub, and C. Lampert, “Optimal geospatial volunteer allocation needs realistic distances,” in 2017 IEEE International Conference on Big Data, Boston, MA, United States, 2017, pp. 3760–3763.","ama":"Pielorz J, Prandtstetter M, Straub M, Lampert C. Optimal geospatial volunteer allocation needs realistic distances. In: 2017 IEEE International Conference on Big Data. IEEE; 2017:3760-3763. doi:10.1109/BigData.2017.8258375","chicago":"Pielorz, Jasmin, Matthias Prandtstetter, Markus Straub, and Christoph Lampert. “Optimal Geospatial Volunteer Allocation Needs Realistic Distances.” In 2017 IEEE International Conference on Big Data, 3760–63. IEEE, 2017. https://doi.org/10.1109/BigData.2017.8258375.","mla":"Pielorz, Jasmin, et al. “Optimal Geospatial Volunteer Allocation Needs Realistic Distances.” 2017 IEEE International Conference on Big Data, IEEE, 2017, pp. 3760–63, doi:10.1109/BigData.2017.8258375.","short":"J. Pielorz, M. Prandtstetter, M. Straub, C. Lampert, in:, 2017 IEEE International Conference on Big Data, IEEE, 2017, pp. 3760–3763."},"quality_controlled":"1","page":"3760 - 3763","month":"12","day":"01","publication_identifier":{"isbn":["978-153862714-3"]},"scopus_import":1,"author":[{"full_name":"Pielorz, Jasmin","first_name":"Jasmin","last_name":"Pielorz","id":"49BC895A-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Prandtstetter, Matthias","last_name":"Prandtstetter","first_name":"Matthias"},{"last_name":"Straub","first_name":"Markus","full_name":"Straub, Markus"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887","first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph"}],"date_updated":"2021-01-12T08:13:55Z","date_created":"2018-12-11T11:48:18Z","oa_version":"None","_id":"750","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","year":"2017","status":"public","publication_status":"published","title":"Optimal geospatial volunteer allocation needs realistic distances","department":[{"_id":"ChLa"}],"publisher":"IEEE","abstract":[{"text":"Modern communication technologies allow first responders to contact thousands of potential volunteers simultaneously for support during a crisis or disaster event. However, such volunteer efforts must be well coordinated and monitored, in order to offer an effective relief to the professionals. In this paper we extend earlier work on optimally assigning volunteers to selected landmark locations. In particular, we emphasize the aspect that obtaining good assignments requires not only advanced computational tools, but also a realistic measure of distance between volunteers and landmarks. Specifically, we propose the use of the Open Street Map (OSM) driving distance instead of he previously used flight distance. We find the OSM driving distance to be better aligned with the interests of volunteers and first responders. Furthermore, we show that relying on the flying distance leads to a substantial underestimation of the number of required volunteers, causing negative side effects in case of an actual crisis situation.","lang":"eng"}],"publist_id":"6906","type":"conference"}]