{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:54:50Z","timestamp":1780055690623,"version":"3.54.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3301876","type":"journal-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T17:22:35Z","timestamp":1691169755000},"page":"14055-14068","source":"Crossref","is-referenced-by-count":12,"title":["A Parametrical Model for Instance-Dependent Label Noise"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6145-0150","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2908-5530","authenticated-orcid":false,"given":"Songhua","family":"Wu","sequence":"additional","affiliation":[{"name":"Trustworthy Machine Learning Lab, School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0855-1646","authenticated-orcid":false,"given":"Erkun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6338-0958","authenticated-orcid":false,"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hongkong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8420-6011","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California Santa Cruz, Santa Cruz, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9581-8849","authenticated-orcid":false,"given":"Min","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7353-5079","authenticated-orcid":false,"given":"Gang","family":"Niu","sequence":"additional","affiliation":[{"name":"RIKEN center for Advanced Intelligence Project, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9640-6472","authenticated-orcid":false,"given":"Tongliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Trustworthy Machine Learning Lab, School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"10789","article-title":"Searching to exploit memorization effect in learning with noisy labels","author":"yao","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref57","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","author":"yao","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref56","article-title":"Meta transition adaptation for robust deep learning with noisy labels","author":"shu","year":"2020"},{"key":"ref15","first-page":"7164","article-title":"How does disagreement benefit co-teaching?","author":"yu","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00945"},{"key":"ref14","article-title":"SIGUA: Forgetting may make learning with noisy labels more robust","author":"han","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref58","first-page":"825","article-title":"Confidence scores make instance-dependent label-noise learning possible","author":"berthon","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","first-page":"12912","article-title":"Clusterability as an alternative to anchor points when learning with noisy labels","author":"zhu","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/792538.792543"},{"key":"ref55","first-page":"10477","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","author":"hendrycks","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5412-1"},{"key":"ref54","first-page":"6403","article-title":"Provably end-to-end label-noise learning without anchor points","author":"li","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"960","article-title":"Decoupling “when to update” from “how to update","author":"malach","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref16","first-page":"8527","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","author":"han","year":"2018","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref19","first-page":"2309","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"jiang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"4331","article-title":"Learning to reweight examples for robust deep learning","author":"ren","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00998"},{"key":"ref50","first-page":"6838","article-title":"Are anchor points really indispensable in label-noise learning?","author":"xia","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref46","first-page":"25302","article-title":"Estimating instance-dependent Bayes-label transition matrix using a deep neural network","author":"yang","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","article-title":"Part-dependent label noise: Towards instance-dependent label noise","author":"xia","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref48","first-page":"97","article-title":"Support vector machines under adversarial label noise","author":"biggio","year":"2011","journal-title":"Proc Asian Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"ref42","article-title":"Parts-dependent label noise: Towards instance-dependent label noise","author":"xia","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"6222","article-title":"L_DMI: A novel information-theoretic loss function for training deep nets robust to label noise","author":"xu","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref44","first-page":"2159","article-title":"Algorithmic stability and hypothesis complexity","author":"liu","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref43","first-page":"1789","article-title":"Learning with bounded instance-and label-dependent label noise","author":"cheng","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2223460"},{"key":"ref8","article-title":"Free lunch for few-shot learning: Distribution calibration","author":"yang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.110"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"ref3","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","author":"li","year":"2020","journal-title":"Proc 23rd Int Conf Artif Intell Statist"},{"key":"ref6","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","first-page":"2691","article-title":"Learning from massive noisy labeled data for image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref81","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref40","article-title":"Peer loss functions: Learning from noisy labels without knowing noise rates","author":"liu","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref84","article-title":"Normalized loss functions for deep learning with noisy labels","author":"ma","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref80","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref35","first-page":"1196","article-title":"Learning with noisy labels","author":"natarajan","year":"2013","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref79","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017"},{"key":"ref34","article-title":"Objects in semantic topology","author":"yang","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2008.926323"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref36","article-title":"Training deep neural-networks using a noise adaptation layer","author":"goldberger","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref75","author":"mohri","year":"2018","journal-title":"Foundations of Machine Learning"},{"key":"ref30","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"2018","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref74","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"bartlett","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref33","first-page":"838","article-title":"A rate of convergence for mixture proportion estimation, with application to learning from noisy labels","author":"scott","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref77","first-page":"297","article-title":"Size-independent sample complexity of neural networks","author":"golowich","year":"2018","journal-title":"Proc Annu Conf Learn Theory"},{"key":"ref32","article-title":"Learning with confident examples: Rank pruning for robust classification with noisy labels","author":"northcutt","year":"2017","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref76","author":"ledoux","year":"2013","journal-title":"Probability in Banach spaces Isoperimetry and Processes"},{"key":"ref2","first-page":"10271","article-title":"Robustness of conditional GANs to noisy labels","author":"thekumparampil","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116829"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00317"},{"key":"ref71","article-title":"Learning with instance-dependent label noise: A sample sieve approach","author":"cheng","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00081"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17319"},{"key":"ref24","first-page":"5836","article-title":"Masking: A new perspective of noisy supervision","author":"han","year":"2018","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref68","article-title":"SELF: Learning to filter noisy labels with self-ensembling","author":"nguyen","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","article-title":"Reliable label correction is a good booster when learning with extremely noisy labels","author":"wang","year":"2022"},{"key":"ref67","article-title":"Early-learning regularization prevents memorization of noisy labels","author":"liu","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350995"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.696"},{"key":"ref69","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","author":"li","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","first-page":"3361","article-title":"Dimensionality-driven learning with noisy labels","author":"ma","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref64","first-page":"11447","article-title":"Error-bounded correction of noisy labels","author":"zheng","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","article-title":"Learning with feature-dependent label noise: A progressive approach","author":"zhang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref66","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","first-page":"308","article-title":"Robust active label correction","author":"kremer","year":"2018","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref65","article-title":"Robust early-learning: Hindering the memorization of noisy labels","author":"xia","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","first-page":"11285","article-title":"Class2Simi: A new perspective on learning with label noise","author":"wu","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"5596","article-title":"Toward robustness against label noise in training deep discriminative neural networks","author":"vahdat","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref29","first-page":"10913","article-title":"Label noise robust domain adaptation","author":"yu","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref60","article-title":"Curriculum loss: Robust learning and generalization against label corruption","author":"lyu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","article-title":"Dataset pruning: Reducing training data by examining generalization influence","author":"yang","year":"2023","journal-title":"Proc 11th Int Conf Learn Representations"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01188"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10209198.pdf?arnumber=10209198","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:48:17Z","timestamp":1701114497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10209198\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":84,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3301876","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}