{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:39:59Z","timestamp":1766158799849,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004044","name":"Kansai University Organization for Research and Development of Innovative Science and Technology (ORDIST) Research Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004044","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3119582","type":"journal-article","created":{"date-parts":[[2021,10,14]],"date-time":"2021-10-14T01:35:03Z","timestamp":1634175303000},"page":"141131-141143","source":"Crossref","is-referenced-by-count":5,"title":["Training Robust Deep Neural Networks on Noisy Labels Using Adaptive Sample Selection With Disagreement"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0713-6878","authenticated-orcid":false,"given":"Hiroshi","family":"Takeda","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0237-7461","authenticated-orcid":false,"given":"Soh","family":"Yoshida","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4492-5991","authenticated-orcid":false,"given":"Mitsuji","family":"Muneyasu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","author":"chen","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00945"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2017.10.026"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.09.023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2012.01.015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref37","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","author":"li","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref36","first-page":"1","article-title":"SELF: Learning to filter noisy labels with self-ensembling","author":"nguyen","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00138"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00342"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00058"},{"journal-title":"Automated Machine Learning Methods Systems Challenges","year":"2018","author":"hutter","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref2","first-page":"2424","article-title":"The multidimensional wisdom of crowds","author":"welinder","year":"2010","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref20","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref22","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 (NeurIPS)"},{"key":"ref21","first-page":"2694","article-title":"Self-paced curriculum learning","author":"jiang","year":"2015","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref24","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","author":"yu","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref23","first-page":"8535","article-title":"Co-teaching: Robust training of deep neural networkswith extremely noisy labels","author":"han","year":"2018","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref26","first-page":"1","article-title":"Can gradient clipping mitigate label noise?","author":"rooyen","year":"2020","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref25","first-page":"10789","article-title":"Searching to exploit memorization effect in learning with noisy labels","author":"yao","year":"2020","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref50","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref10","first-page":"139","article-title":"CurriculumNet: Weakly supervised learning from large-scale web images","author":"guo","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref11","first-page":"1","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref40","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"2017","author":"tarvainen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"233","article-title":"A closer look at memorization in deep networks","author":"arpit","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref13","first-page":"1","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"reed","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref15","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 Conf Neural Inf Process Syst (NeurIPS)"},{"article-title":"Statistical language models based on neural networks","year":"2012","author":"mikolov","key":"ref16"},{"key":"ref17","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"1","article-title":"Can gradient clipping mitigate label noise?","author":"menon","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref19","first-page":"92","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume":"2018","author":"jiang","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5412-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298894"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.133"},{"key":"ref8","article-title":"Web vision database: Visual learning and understanding from web data","author":"li","year":"2017","journal-title":"arXiv 1708 02862"},{"key":"ref7","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 (CVPR)"},{"key":"ref49","first-page":"1","article-title":"Can gradient clipping mitigate label noise?","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref9","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume":"97","author":"song","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref48","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comp Vis (ECCV)"},{"key":"ref47","first-page":"1","article-title":"Training deep neural-networks using a noise adaptation layer","author":"goldberger","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567393"},{"key":"ref41","first-page":"1","article-title":"MixMatch: A holistic approach to semi-supervised learning","author":"berthelot","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107332"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09568980.pdf?arnumber=9568980","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T22:15:38Z","timestamp":1645481738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9568980\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3119582","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}