@inproceedings{8724, abstract = {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 known 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 corrupt 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 participants are malicious. }, author = {Konstantinov, Nikola H and Frantar, Elias and Alistarh, Dan-Adrian and Lampert, Christoph}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, issn = {2640-3498}, location = {Online}, pages = {5416--5425}, publisher = {ML Research Press}, title = {{On the sample complexity of adversarial multi-source PAC learning}}, volume = {119}, year = {2020}, } @phdthesis{8390, abstract = {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 for 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 dissimilar domains. }, author = {Royer, Amélie}, isbn = {978-3-99078-007-7}, issn = {2663-337X}, pages = {197}, publisher = {Institute of Science and Technology Austria}, title = {{Leveraging structure in Computer Vision tasks for flexible Deep Learning models}}, doi = {10.15479/AT:ISTA:8390}, year = {2020}, } @inproceedings{8186, abstract = {Numerous methods have been proposed for probabilistic generative modelling of 3D objects. However, none of these is able to produce textured objects, which renders them of limited use for practical tasks. In this work, we present the first generative model of textured 3D meshes. Training such a model would traditionally require a large dataset of textured meshes, but unfortunately, existing datasets of meshes lack detailed textures. We instead propose a new training methodology that allows learning from collections of 2D images without any 3D information. To do so, we train our model to explain a distribution of images by modelling each image as a 3D foreground object placed in front of a 2D background. Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set. A well-known problem when generating meshes with deep networks is the emergence of self-intersections, which are problematic for many use-cases. As a second contribution we therefore introduce a new generation process for 3D meshes that guarantees no self-intersections arise, based on the physical intuition that faces should push one another out of the way as they move. We conduct extensive experiments on our approach, reporting quantitative and qualitative results on both synthetic data and natural images. These show our method successfully learns to generate plausible and diverse textured 3D samples for five challenging object classes.}, author = {Henderson, Paul M and Tsiminaki, Vagia and Lampert, Christoph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {Virtual}, pages = {7498--7507}, publisher = {IEEE}, title = {{Leveraging 2D data to learn textured 3D mesh generation}}, doi = {10.1109/CVPR42600.2020.00752}, year = {2020}, } @article{6944, abstract = {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.}, author = {Sun, Rémy and Lampert, Christoph}, issn = {1573-1405}, journal = {International Journal of Computer Vision}, number = {4}, pages = {970--995}, publisher = {Springer Nature}, title = {{KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications}}, doi = {10.1007/s11263-019-01232-x}, volume = {128}, year = {2020}, } @book{7171, abstract = {Wissen Sie, was sich hinter künstlicher Intelligenz und maschinellem Lernen verbirgt? Dieses 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. Ein 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!}, editor = {Kersting, Kristian and Lampert, Christoph and Rothkopf, Constantin}, isbn = {978-3-658-26762-9}, pages = {XIV, 245}, publisher = {Springer Nature}, title = {{Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt}}, doi = {10.1007/978-3-658-26763-6}, year = {2019}, } @inproceedings{6942, abstract = {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.}, author = {Ashok, Pranav and Brázdil, Tomáš and Chatterjee, Krishnendu and Křetínský, Jan and Lampert, Christoph and Toman, Viktor}, booktitle = {16th International Conference on Quantitative Evaluation of Systems}, isbn = {9783030302801}, issn = {0302-9743}, location = {Glasgow, United Kingdom}, pages = {109--128}, publisher = {Springer Nature}, title = {{Strategy representation by decision trees with linear classifiers}}, doi = {10.1007/978-3-030-30281-8_7}, volume = {11785}, year = {2019}, } @article{6554, abstract = {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.}, author = {Xian, Yongqin and Lampert, Christoph and Schiele, Bernt and Akata, Zeynep}, issn = {1939-3539}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, number = {9}, pages = {2251 -- 2265}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, title = {{Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly}}, doi = {10.1109/tpami.2018.2857768}, volume = {41}, year = {2019}, } @inproceedings{7479, abstract = {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. Experiments 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.}, author = {Bui Thi Mai, Phuong and Lampert, Christoph}, booktitle = {IEEE International Conference on Computer Vision}, isbn = {9781728148038}, issn = {15505499}, location = {Seoul, Korea}, pages = {1355--1364}, publisher = {IEEE}, title = {{Distillation-based training for multi-exit architectures}}, doi = {10.1109/ICCV.2019.00144}, volume = {2019-October}, year = {2019}, } @inproceedings{7640, abstract = {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.}, author = {Kolesnikov, Alexander and Kuznetsova, Alina and Lampert, Christoph and Ferrari, Vittorio}, booktitle = {Proceedings of the 2019 International Conference on Computer Vision Workshop}, isbn = {9781728150239}, location = {Seoul, South Korea}, publisher = {IEEE}, title = {{Detecting visual relationships using box attention}}, doi = {10.1109/ICCVW.2019.00217}, year = {2019}, } @inproceedings{6569, abstract = {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.}, author = {Bui Thi Mai, Phuong and Lampert, Christoph}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, location = {Long Beach, CA, United States}, pages = {5142--5151}, publisher = {ML Research Press}, title = {{Towards understanding knowledge distillation}}, volume = {97}, year = {2019}, }