{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:39:41Z","timestamp":1783953581389,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Brazil National Council for Scientific and Technological Development","award":["141487\/2020-8"],"award-info":[{"award-number":["141487\/2020-8"]}]},{"name":"Brazil National Council for Scientific and Technological Development","award":["304619\/2022-1"],"award-info":[{"award-number":["304619\/2022-1"]}]},{"name":"Brazil National Council for Scientific and Technological Development","award":["402516\/2024-9"],"award-info":[{"award-number":["402516\/2024-9"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3548510","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T18:52:47Z","timestamp":1741200767000},"page":"43843-43860","source":"Crossref","is-referenced-by-count":3,"title":["CCT: A Cyclic Co-Teaching Approach to Train Deep Neural Networks With Noisy Labels"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8335-9796","authenticated-orcid":false,"given":"Jorge K. S.","family":"Kamassury","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Federal University of Santa Catarina (UFSC), Florianópolis, Santa Catarina, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henrique","family":"Pickler","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Federal University of Santa Catarina (UFSC), Florianópolis, Santa Catarina, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-8436","authenticated-orcid":false,"given":"Filipe R.","family":"Cordeiro","sequence":"additional","affiliation":[{"name":"Department of Computing, Visual Computing Laboratory, Federal Rural University of Pernambuco (UFRPE), Recife, Pernambuco, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6290-7968","authenticated-orcid":false,"given":"Danilo","family":"Silva","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Federal University of Santa Catarina (UFSC), Florianópolis, Santa Catarina, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101759"},{"key":"ref6","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020","journal-title":"arXiv:2011.04406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref8","first-page":"7164","article-title":"How does disagreement help generalization against label corruption","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475622"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00342"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.08.008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119008"},{"key":"ref14","first-page":"792","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref16","first-page":"6543","article-title":"Normalized loss functions for deep learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ma"},{"key":"ref17","first-page":"559","article-title":"L_DMI: A novel information-theoretic loss function for training deep nets robust to label noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref19","first-page":"10477","article-title":"Using trusted data to train deep networks on labels corrupted by severe noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Hendrycks"},{"key":"ref20","first-page":"1003","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chang"},{"key":"ref21","first-page":"1917","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Shu"},{"key":"ref22","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ren"},{"key":"ref23","first-page":"1","article-title":"Training deep neural networks on noisy labels with bootstrapping","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Reed"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102930"},{"key":"ref26","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00524"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107426"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/e26070589"},{"key":"ref31","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jiang"},{"key":"ref32","first-page":"961","article-title":"Decoupling \u2018when to update\u2019 from \u2018how to update","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Malach"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00176"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.03.021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00046"},{"key":"ref36","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref37","first-page":"5049","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Berthelot"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123846"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111860"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.08.060"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref44","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3394552"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref47","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hendrycks"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref49","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref50","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Song"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00571"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1149\/2754-2726\/ac75f5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10912480.pdf?arnumber=10912480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:43:05Z","timestamp":1742233385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10912480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3548510","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}