{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:32:13Z","timestamp":1765233133900,"version":"3.37.3"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tpami.2021.3094662","type":"journal-article","created":{"date-parts":[[2021,7,7]],"date-time":"2021-07-07T20:13:27Z","timestamp":1625688807000},"page":"7296-7306","source":"Crossref","is-referenced-by-count":15,"title":["Wasserstein Adversarial Regularization for Learning With Label Noise"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4458-7029","authenticated-orcid":false,"given":"Kilian","family":"Fatras","sequence":"first","affiliation":[{"name":"CNRS, INRIA, IRISA, UMR 6074, University Bretagne Sud, Lorient Cedex, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4466-017X","authenticated-orcid":false,"given":"Bharath Bhushan","family":"Damodaran","sequence":"additional","affiliation":[{"name":"InterDigital R&D, Rennes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4738-2416","authenticated-orcid":false,"given":"Sylvain","family":"Lobry","sequence":"additional","affiliation":[{"name":"LIPADE, Université de Paris, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4212-6627","authenticated-orcid":false,"given":"Remi","family":"Flamary","sequence":"additional","affiliation":[{"name":"CMAP, École Polytechnique, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0374-2459","authenticated-orcid":false,"given":"Devis","family":"Tuia","sequence":"additional","affiliation":[{"name":"Ecole Polytechnique Fédérale de Lausanne, Sion, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1353-0126","authenticated-orcid":false,"given":"Nicolas","family":"Courty","sequence":"additional","affiliation":[{"name":"CNRS, INRIA, IRISA, UMR 6074, University Bretagne Sud, Lorient Cedex, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.133"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_19"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref5","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_47"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2771298"},{"key":"ref8","first-page":"97","article-title":"Support vector machines under adversarial label noise","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Biggio"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.606"},{"key":"ref10","first-page":"5601","article-title":"Toward robustness against label noise in training deep discriminative neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"key":"ref14","first-page":"1196","article-title":"Learning with noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Natarajan"},{"key":"ref15","first-page":"2309","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref16","first-page":"4331","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref18","first-page":"125","article-title":"Learning from corrupted binary labels via class-probability estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Menon"},{"article-title":"Learning from noisy labels with deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sukhbaatar","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref21","first-page":"10477","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hendrycks"},{"key":"ref22","first-page":"1","article-title":"Training deep neural networks on noisy labels with bootstrapping","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reed"},{"key":"ref23","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref26","first-page":"8536","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref27","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref29","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref30","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref32","first-page":"8792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref34","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0088"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409061"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587348"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.04.027"},{"key":"ref43","first-page":"1","article-title":"Label smoothing and logit squeezing: A replacement for adversarial training?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shafahi"},{"article-title":"Adversarial robustness via adversarial label-smoothing","year":"2019","author":"Goibert","key":"ref44"},{"key":"ref45","first-page":"2053","article-title":"Learning with a Wasserstein loss","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Frogner"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref47","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref48","first-page":"5864","article-title":"Differential properties of sinkhorn approximation for learning with wasserstein distance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luise"},{"key":"ref49","first-page":"1964","article-title":"Near-linear time approximation algorithms for optimal transport via sinkhorn iteration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Altschuler"},{"key":"ref50","first-page":"1608","article-title":"Learning generative models with sinkhorn divergences","volume-title":"Proc. 21st Int. Conf. Artif. Intell. Statist.","author":"Genevay"},{"key":"ref51","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mikolov"},{"issue":"1","key":"ref52","first-page":"533","article-title":"Ground metric learning","volume":"15","author":"Cuturi","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","first-page":"4862","article-title":"Supervised word Mover\u2019s distance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"issue":"80","key":"ref54","first-page":"1","article-title":"Learning to match via inverse optimal transport","volume":"20","author":"Li","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","first-page":"1","article-title":"Sobolev GAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mroueh"},{"key":"ref56","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","first-page":"10","article-title":"Learning with symmetric label noise: The importance of being unhinged","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rooyen"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref60"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1017\/9781108924238.008"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_28"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102863"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3390\/rs10010144"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00906"},{"key":"ref70","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Oord"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9893033\/09477020.pdf?arnumber=9477020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:12:26Z","timestamp":1705014746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9477020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3094662","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}