{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T02:06:23Z","timestamp":1793844383348,"version":"4.6.1"},"reference-count":174,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government","award":["2020-0-00862"],"award-info":[{"award-number":["2020-0-00862"]}],"id":[{"id":"https:\/\/ror.org\/01g0hqq23","id-type":"ROR","asserted-by":"crossref"}]},{"name":"DB4DL: High-Usability and Performance In-Memory Distributed DBMS for Deep Learning"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tnnls.2022.3152527","type":"journal-article","created":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T15:45:04Z","timestamp":1646667904000},"page":"8135-8153","source":"Crossref","is-referenced-by-count":1037,"title":["Learning From Noisy Labels With Deep Neural Networks: A Survey"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1105-0818","authenticated-orcid":false,"given":"Hwanjun","family":"Song","sequence":"first","affiliation":[{"name":"NAVER AI Laboratory, Seongnam, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minseok","family":"Kim","sequence":"additional","affiliation":[{"name":"Graduate School of Knowledge Service Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8430-0294","authenticated-orcid":false,"given":"Dongmin","family":"Park","sequence":"additional","affiliation":[{"name":"Graduate School of Knowledge Service Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yooju","family":"Shin","sequence":"additional","affiliation":[{"name":"Graduate School of Knowledge Service Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8711-7732","authenticated-orcid":false,"given":"Jae-Gil","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate School of Knowledge Service Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","first-page":"97","article-title":"Support vector machines under adversarial label noise","author":"biggio","year":"2011","journal-title":"Proc ACML"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-788"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57454-7_53"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.01.017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74958-5_71"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2005.845141"},{"key":"ref55","first-page":"74","article-title":"Comparative validation of graphical models for learning tumor segmentations from noisy manual annotations","author":"kaster","year":"2010","journal-title":"Proc MICCAI"},{"key":"ref168","first-page":"702","article-title":"Identifying and correcting label bias in machine learning","author":"jiang","year":"2020","journal-title":"Proc AISTATS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1189"},{"key":"ref169","first-page":"5190","article-title":"Robust optimization for fairness with noisy protected groups","author":"wang","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445915"},{"key":"ref51","first-page":"708","article-title":"Loss factorization, weakly supervised learning and label noise robustness","author":"patrini","year":"2016","journal-title":"Proc ICML"},{"key":"ref50","first-page":"10","article-title":"Learning with symmetric label noise: The importance of being unhinged","author":"van rooyen","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref173","article-title":"Understanding the interaction of adversarial training with noisy labels","author":"zhu","year":"2021","journal-title":"arXiv 2102 03482"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-018-09679-z"},{"key":"ref171","first-page":"12192","article-title":"Are labels required for improving adversarial robustness?","author":"uesato","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref172","first-page":"1","article-title":"Wasserstein adversarial regularization (WAR) on label noise","author":"damodaran","year":"2020","journal-title":"Proc ICLR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89376-9_10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/088395100117124"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2223460"},{"key":"ref47","first-page":"567","article-title":"Learning to label aerial images from noisy data","author":"mnih","year":"2012","journal-title":"Proc ICML"},{"key":"ref42","first-page":"123","article-title":"Using boosting to detect noisy data","author":"wheway","year":"2000","journal-title":"Proc PRICAI"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1142\/9789813144552_0006"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2012.01.015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-012-0299-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.09.081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767830"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc ACL"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S1930297500002205"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132914"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-017-9321-y"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/305"},{"key":"ref101","first-page":"6226","article-title":"Peer loss functions: Learning from noisy labels without knowing noise rates","author":"liu","year":"2020","journal-title":"Proc ICML"},{"key":"ref40","first-page":"1","article-title":"Training deep neural-networks using a noise adaptation layer","author":"goldberger","year":"2017","journal-title":"Proc ICLR"},{"key":"ref35","first-page":"2280","article-title":"Adversarial examples are a natural consequence of test error in noise","author":"gilmer","year":"2019","journal-title":"Proc ICML"},{"key":"ref34","first-page":"1646","article-title":"Generalized no free lunch theorem for adversarial robustness","author":"dohmatob","year":"2019","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/63.3.581"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014536"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref148","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","article-title":"A survey of label-noise representation learning: Past, present and future","author":"han","year":"2020","journal-title":"arXiv 2011 04406"},{"key":"ref149","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","author":"berthelot","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref33","first-page":"1632","article-title":"Robustness of classifiers: From adversarial to random noise","author":"fawzi","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref146","first-page":"21382","article-title":"A topological filter for learning with label noise","author":"wu","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref32","first-page":"5689","article-title":"GAIN: Missing data imputation using generative adversarial nets","author":"yoon","year":"2018","journal-title":"Proc ICML"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00013"},{"key":"ref39","first-page":"1196","article-title":"Learning with noisy labels","author":"natarajan","year":"2013","journal-title":"Proc NeurIPS"},{"key":"ref38","author":"bishop","year":"2006","journal-title":"Pattern Recognition Machine Learning"},{"key":"ref155","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref156","author":"krizhevsky","year":"2014","journal-title":"CIFAR-10 and CIFAR-100 Datasets"},{"key":"ref153","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 AISTATS"},{"key":"ref154","author":"lecun","year":"1998","journal-title":"MNIST handwritten digit database 1998"},{"key":"ref151","first-page":"6403","article-title":"Provably end-to-end label-noise learning without anchor points","author":"li","year":"2021","journal-title":"Proc ICML"},{"key":"ref152","author":"pleiss","year":"2020","journal-title":"Detecting Noisy Training Data With Loss Curves"},{"key":"ref150","first-page":"1","article-title":"Robust curriculum learning: From clean label detection to noisy label self-correction","author":"zhou","year":"2021","journal-title":"Proc ICLR"},{"key":"ref24","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1992","journal-title":"Proc NeurIPS"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"shorten","year":"2019","journal-title":"J Big Data"},{"key":"ref26","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref25","first-page":"1929","article-title":"DropOut: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_19"},{"key":"ref159","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","author":"wei","year":"2011","journal-title":"arXiv 2110 12088"},{"key":"ref22","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref157","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NeurIPSW"},{"key":"ref21","first-page":"233","article-title":"A closer look at memorization in deep networks","author":"arpit","year":"2017","journal-title":"Proc ICML"},{"key":"ref158","first-page":"1","article-title":"Cs231n convolutional neural networks for visual recognition","volume":"1","author":"karpathy","year":"2016","journal-title":"Neural Netw"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-016-9491-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-004-0751-8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0694-9_38"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref167","first-page":"1","article-title":"Equality of opportunity in supervised learning","author":"hardt","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref164","first-page":"18","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","volume":"2","author":"krasin","year":"2017","journal-title":"Dataset"},{"key":"ref165","article-title":"Evaluating multi-label classifiers with noisy labels","author":"zhao","year":"2021","journal-title":"arXiv 2102 08427"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.4018\/jdwm.2007070101"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.009"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-018-0750-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref12","first-page":"489","article-title":"Classification with asymmetric label noise: Consistency and maximal denoising","author":"scott","year":"2013","journal-title":"Proc COLT"},{"key":"ref15","first-page":"870","article-title":"Adversarial label flips attack on support vector machines","author":"xiao","year":"2012","journal-title":"Proc ECAI"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00931"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1097\/01.pas.0000135519.34847.f6"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref97","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref126","first-page":"1","article-title":"Learning to learn from weak supervision by full supervision","author":"dehghani","year":"2017","journal-title":"Proc NeurIPSW"},{"key":"ref96","first-page":"7","article-title":"Approximation with artificial neural networks","volume":"24","author":"cs\u00e1ji","year":"2001","journal-title":"Fac Sci Etvs Lornd Univ Hung"},{"key":"ref127","article-title":"Avoiding your teacher’s mistakes: Training neural networks with controlled weak supervision","author":"dehghani","year":"2017","journal-title":"arXiv 1711 00313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-011-0124-6"},{"key":"ref99","first-page":"1","article-title":"Curriculum loss: Robust learning and generalization against label corruption","author":"lyu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref124","first-page":"1917","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","author":"shu","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20078"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00458"},{"key":"ref17","article-title":"Web vision database: Visual learning and understanding from web data","author":"li","year":"2017","journal-title":"arXiv 1708 02862"},{"key":"ref16","first-page":"2691","article-title":"Learning from massive noisy labeled data for image classification","author":"xiao","year":"2015","journal-title":"Proc CVPR"},{"key":"ref19","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","author":"song","year":"2019","journal-title":"Proc ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3390\/e19070313"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00906"},{"key":"ref92","first-page":"1","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"Proc ICLR"},{"key":"ref134","first-page":"5739","article-title":"Learning with bad training data via iterative trimmed loss minimization","author":"shen","year":"2019","journal-title":"Proc ICML"},{"key":"ref95","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref131","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","author":"jiang","year":"2018","journal-title":"Proc ICML"},{"key":"ref94","first-page":"6448","article-title":"Does label smoothing mitigate label noise?","author":"lukasik","year":"2020","journal-title":"Proc ICLR"},{"key":"ref132","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","author":"yu","year":"2019","journal-title":"Proc ICML"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17319"},{"key":"ref91","first-page":"1","article-title":"Open-set label noise can improve robustness against inherent label noise","author":"wei","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref90","first-page":"1","article-title":"Robust early-learning: Hindering the memorization of noisy labels","author":"xia","year":"2021","journal-title":"Proc ICLR"},{"key":"ref89","first-page":"1","article-title":"Can gradient clipping mitigate label noise?","author":"menon","year":"2020","journal-title":"Proc ICLR"},{"key":"ref139","first-page":"1","article-title":"Identity Crisis: Memorization and generalization under extreme overparameterization","author":"zhang","year":"2020","journal-title":"Proc ICLR"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01150"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467222"},{"key":"ref85","first-page":"3763","article-title":"Robust inference via generative classifiers for handling noisy labels","author":"lee","year":"2019","journal-title":"Proc ICML"},{"key":"ref138","first-page":"1","article-title":"Deep nets don’t learn via memorization","author":"krueger","year":"2017","journal-title":"Proc ICLRW"},{"key":"ref88","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","author":"hendrycks","year":"2019","journal-title":"Proc ICML"},{"key":"ref135","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","author":"chen","year":"2019","journal-title":"Proc ICML"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_38"},{"key":"ref136","first-page":"1","article-title":"SELF: Learning to filter noisy labels with self-ensembling","author":"nguyen","year":"2020","journal-title":"Proc ICLR"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_19"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00342"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877939"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"ref84","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref142","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","author":"li","year":"2020","journal-title":"Proc ICLR"},{"key":"ref83","article-title":"Extended T: Learning with mixed closed-set and open-set noisy labels","author":"xia","year":"2020","journal-title":"arXiv 2012 00932"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref140","first-page":"10789","article-title":"Searching to exploit memorization effect in learning with noisy labels","author":"yao","year":"2020","journal-title":"Proc ICML"},{"key":"ref141","article-title":"How does early stopping help generalization against label noise?","author":"song","year":"2019","journal-title":"arXiv 1911 08059"},{"key":"ref80","first-page":"5836","article-title":"Masking: A new perspective of noisy supervision","author":"han","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref79","first-page":"1","article-title":"Training deep neural-networks using a noise adaptation layer","author":"goldberger","year":"2017","journal-title":"Proc ICLR"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2699783"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0121"},{"key":"ref109","first-page":"1002","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","author":"chang","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref106","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","author":"ren","year":"2018","journal-title":"Proc ICML"},{"key":"ref107","first-page":"10456","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","author":"hendrycks","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref104","first-page":"14987","article-title":"Robust bi-tempered logistic loss based on Bregman divergences","author":"amid","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref74","first-page":"1","article-title":"Noise against noise: Stochastic label noise helps combat inherent label noise","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref105","first-page":"6543","article-title":"Normalized loss functions for deep learning with noisy labels","author":"ma","year":"2020","journal-title":"Proc ICML"},{"key":"ref77","first-page":"1","article-title":"Training convolutional networks with noisy labels","author":"sukhbaatar","year":"2015","journal-title":"Proc ICLRW"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3371158.3371169"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472164"},{"key":"ref103","first-page":"2388","article-title":"Two-temperature logistic regression based on the tsallis divergence","author":"amid","year":"2019","journal-title":"Proc AISTATS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.12.100"},{"key":"ref111","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","author":"ma","year":"2018","journal-title":"Proc ICML"},{"key":"ref70","first-page":"960","article-title":"Decoupling ‘when to update’ from ‘how to update","author":"malach","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref112","first-page":"8527","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","author":"han","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","first-page":"4071","article-title":"Improving generalization by controlling label-noise information in neural network weights","author":"harutyunyan","year":"2020","journal-title":"Proc ICML"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10276"},{"key":"ref110","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","author":"arazo","year":"2019","journal-title":"Proc ICML"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref119","first-page":"19365","article-title":"Self-adaptive training: Beyond empirical risk minimization","author":"huang","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-1997-1405"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref69","first-page":"1","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"reed","year":"2015","journal-title":"Proc ICLR"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00953"},{"key":"ref64","first-page":"782","article-title":"Robust deep ordinal regression under label noise","author":"garg","year":"2020","journal-title":"Proc ACML"},{"key":"ref115","article-title":"Approximating instance-dependent noise via instance-confidence embedding","author":"zhang","year":"2021","journal-title":"arXiv 2103 13569"},{"key":"ref63","first-page":"1789","article-title":"Learning with bounded instance and label-dependent label noise","author":"cheng","year":"2020","journal-title":"Proc ICML"},{"key":"ref116","article-title":"Estimating instance-dependent label-noise transition matrix using DNNs","author":"yang","year":"2021","journal-title":"arXiv 2105 13001"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-018-5715-3"},{"key":"ref113","first-page":"1","article-title":"Are anchor points really indispensable in label-noise learning?","author":"xia","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref65","first-page":"1","article-title":"Simple and effective regularization methods for training on noisily labeled data with generalization guarantee","author":"hu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref114","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","author":"yao","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref60","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume":"33","author":"liu","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17363"},{"key":"ref123","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc ICML"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68474-1_5"},{"key":"ref61","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 AISTATS"},{"key":"ref121","first-page":"11447","article-title":"Error-bounded correction of noisy labels","author":"zheng","year":"2020","journal-title":"Proc ICML"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10299535\/09729424.pdf?arnumber=9729424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:30:01Z","timestamp":1699885801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9729424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":174,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3152527","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}