{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:54:38Z","timestamp":1775325278485,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376282"],"award-info":[{"award-number":["62376282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372459"],"award-info":[{"award-number":["62372459"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,9]]},"DOI":"10.1109\/tpami.2024.3382138","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T18:55:02Z","timestamp":1711652102000},"page":"6341-6354","source":"Crossref","is-referenced-by-count":13,"title":["Tackling Noisy Labels With Network Parameter Additive Decomposition"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5970-7961","authenticated-orcid":false,"given":"Jingyi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Intelligent Data Science, College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3615-0919","authenticated-orcid":false,"given":"Xiaobo","family":"Xia","sequence":"additional","affiliation":[{"name":"Trustworthy Machine Learning Lab, School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Intelligent Data Science, College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6987-3972","authenticated-orcid":false,"given":"Xinghao","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6997-0406","authenticated-orcid":false,"given":"Wenjing","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Intelligent Data Science, College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6338-0958","authenticated-orcid":false,"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong"}]},{"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, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00945"},{"key":"ref3","first-page":"1173","article-title":"Combinatorial inference against label noise","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Seo"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3131937"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00251"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3242148"},{"key":"ref7","first-page":"11447","article-title":"Error-bounded correction of noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref8","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref9","first-page":"11285","article-title":"Class2Simi: A noise reduction perspective on learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref10","first-page":"10789","article-title":"Searching to exploit memorization effect in learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902115"},{"key":"ref12","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo"},{"key":"ref13","first-page":"1","article-title":"Understanding deep learning requires rethinking generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref14","first-page":"2206","article-title":"Can cross entropy loss be robust to label noise?","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Feng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"ref16","first-page":"5907","article-title":"Selfie: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183841"},{"key":"ref18","first-page":"1","article-title":"Noise against noise: Stochastic label noise helps combat inherent label noise","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref19","first-page":"4006","article-title":"SIGUA: Forgetting may make learning with noisy labels more robust","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref20","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref21","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref22","first-page":"4313","article-title":"Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Li"},{"key":"ref23","first-page":"12","article-title":"Simple and effective regularization methods for training on noisily labeled data with generalization guarantee","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref24","article-title":"How does early stopping help generalization against label noise?","author":"Song","year":"2019"},{"key":"ref25","article-title":"Scalable and order-robust continual learning with additive parameter decomposition","author":"Yoon","year":"2019"},{"key":"ref26","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877939"},{"key":"ref28","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":"ref29","first-page":"4331","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren"},{"key":"ref30","first-page":"8527","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":"ref31","first-page":"7164","article-title":"How does disagreement benefit co-teaching?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00176"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17363"},{"key":"ref39","first-page":"15","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref41","first-page":"10","article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goldberger"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref43","first-page":"6838","article-title":"Are anchor points really indispensable in label-noise learning?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xia"},{"key":"ref44","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yao"},{"issue":"3","key":"ref45","first-page":"3047","article-title":"Extended T: Learning with mixed closed-set and open-set noisy labels","volume":"45","author":"Xia","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00998"},{"key":"ref47","article-title":"Meta transition adaptation for robust deep learning with noisy labels","author":"Shu","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00335"},{"key":"ref49","first-page":"21475","article-title":"Identifiability of label noise transition matrix","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref51","first-page":"8778","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref53","first-page":"6543","article-title":"Normalized loss functions for deep learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref54","first-page":"22","article-title":"Curriculum loss: Robust learning and generalization against label corruption","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lyu"},{"key":"ref55","first-page":"36868","article-title":"Mitigating memorization of noisy labels by clipping the model prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref56","article-title":"Improve noise tolerance of robust loss via noise-awareness","author":"Ding","year":"2023"},{"key":"ref57","article-title":"The MNIST database of handwritten digits","author":"LeCun","year":"2012"},{"key":"ref58","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref59","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00041"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00014"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00019"},{"key":"ref63","first-page":"11465","article-title":"Coresets for robust training of neural networks against noisy labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mirzasoleiman"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00044"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01150"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00524"},{"key":"ref67","first-page":"7597","article-title":"Part-dependent label noise: Towards instance-dependent label noise","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xia"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref70","first-page":"1","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei"},{"key":"ref71","first-page":"14","article-title":"Sample selection with uncertainty of losses for learning with noisy labels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia"},{"key":"ref72","first-page":"34","article-title":"Self: Learning to filter noisy labels with self-ensembling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nguyen"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref74","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.05431"},{"issue":"11","key":"ref76","first-page":"2579","article-title":"Visualizing data using t-SNE,","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10627928\/10480647.pdf?arnumber=10480647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:45:19Z","timestamp":1723052719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":76,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3382138","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":[[2024,9]]}}}