{"conference":{"start_date":"2021-07-18","location":"Virtual","name":"ML: Machine Learning","end_date":"2021-07-24"},"main_file_link":[{"url":"https://proceedings.mlr.press/v139/babaiee21a","open_access":"1"}],"date_updated":"2022-05-04T15:02:27Z","publication":"Proceedings of the 38th International Conference on Machine Learning","_id":"10668","file":[{"content_type":"application/pdf","date_created":"2022-01-26T07:38:32Z","file_size":4246561,"success":1,"file_id":"10681","relation":"main_file","checksum":"d30eae62561bb517d9f978437d7677db","date_updated":"2022-01-26T07:38:32Z","creator":"mlechner","file_name":"babaiee21a.pdf","access_level":"open_access"}],"acknowledgement":"Z.B. is supported by the Doctoral College Resilient Embedded Systems, which is run jointly by the TU Wien’s Faculty of Informatics and the UAS Technikum Wien. R.G. is partially supported by the Horizon 2020 Era-Permed project Persorad, and ECSEL Project grant no. 783163 (iDev40). R.H and D.R were partially supported by Boeing and MIT. M.L. is supported in part by the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award).","page":"478-489","publication_status":"published","license":"https://creativecommons.org/licenses/by-nc-nd/3.0/","day":"01","year":"2021","publisher":"ML Research Press","volume":139,"oa":1,"language":[{"iso":"eng"}],"quality_controlled":"1","project":[{"call_identifier":"FWF","name":"The Wittgenstein Prize","grant_number":"Z211","_id":"25F42A32-B435-11E9-9278-68D0E5697425"}],"abstract":[{"text":"Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks with two residual components, ubiquitous in the visual processing system of vertebrates: On-center and off-center pathways, with an excitatory center and inhibitory surround; OOCS for short. The On-center pathway is excited by the presence of a light stimulus in its center, but not in its surround, whereas the Off-center pathway is excited by the absence of a light stimulus in its center, but not in its surround. We design OOCS pathways via a difference of Gaussians, with their variance computed analytically from the size of the receptive fields. OOCS pathways complement each other in their response to light stimuli, ensuring this way a strong edge-detection capability, and as a result an accurate and robust inference under challenging lighting conditions. We provide extensive empirical evidence showing that networks supplied with OOCS pathways gain accuracy and illumination-robustness from the novel edge representation, compared to other baselines.","lang":"eng"}],"citation":{"ista":"Babaiee Z, Hasani R, Lechner M, Rus D, Grosu R. 2021. On-off center-surround receptive fields for accurate and robust image classification. Proceedings of the 38th International Conference on Machine Learning. ML: Machine Learning, PMLR, vol. 139, 478–489.","ama":"Babaiee Z, Hasani R, Lechner M, Rus D, Grosu R. On-off center-surround receptive fields for accurate and robust image classification. In: <i>Proceedings of the 38th International Conference on Machine Learning</i>. Vol 139. ML Research Press; 2021:478-489.","short":"Z. Babaiee, R. Hasani, M. Lechner, D. Rus, R. Grosu, in:, Proceedings of the 38th International Conference on Machine Learning, ML Research Press, 2021, pp. 478–489.","chicago":"Babaiee, Zahra, Ramin Hasani, Mathias Lechner, Daniela Rus, and Radu Grosu. “On-off Center-Surround Receptive Fields for Accurate and Robust Image Classification.” In <i>Proceedings of the 38th International Conference on Machine Learning</i>, 139:478–89. ML Research Press, 2021.","apa":"Babaiee, Z., Hasani, R., Lechner, M., Rus, D., &#38; Grosu, R. (2021). On-off center-surround receptive fields for accurate and robust image classification. In <i>Proceedings of the 38th International Conference on Machine Learning</i> (Vol. 139, pp. 478–489). Virtual: ML Research Press.","mla":"Babaiee, Zahra, et al. “On-off Center-Surround Receptive Fields for Accurate and Robust Image Classification.” <i>Proceedings of the 38th International Conference on Machine Learning</i>, vol. 139, ML Research Press, 2021, pp. 478–89.","ieee":"Z. Babaiee, R. Hasani, M. Lechner, D. Rus, and R. Grosu, “On-off center-surround receptive fields for accurate and robust image classification,” in <i>Proceedings of the 38th International Conference on Machine Learning</i>, Virtual, 2021, vol. 139, pp. 478–489."},"intvolume":"       139","author":[{"full_name":"Babaiee, Zahra","last_name":"Babaiee","first_name":"Zahra"},{"first_name":"Ramin","full_name":"Hasani, Ramin","last_name":"Hasani"},{"id":"3DC22916-F248-11E8-B48F-1D18A9856A87","first_name":"Mathias","last_name":"Lechner","full_name":"Lechner, Mathias"},{"first_name":"Daniela","full_name":"Rus, Daniela","last_name":"Rus"},{"full_name":"Grosu, Radu","last_name":"Grosu","first_name":"Radu"}],"tmp":{"name":"Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)","short":"CC BY-NC-ND (3.0)","image":"/images/cc_by_nc_nd.png","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode"},"department":[{"_id":"GradSch"},{"_id":"ToHe"}],"alternative_title":["PMLR"],"title":"On-off center-surround receptive fields for accurate and robust image classification","status":"public","ddc":["000"],"month":"07","publication_identifier":{"issn":["2640-3498"]},"type":"conference","user_id":"2EBD1598-F248-11E8-B48F-1D18A9856A87","has_accepted_license":"1","article_processing_charge":"No","date_published":"2021-07-01T00:00:00Z","file_date_updated":"2022-01-26T07:38:32Z","oa_version":"Published Version","date_created":"2022-01-25T15:46:33Z"}