{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:24Z","timestamp":1792786944308,"version":"4.5.0"},"reference-count":126,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"RGC Young Collaborative Research","award":["C2005-24Y"],"award-info":[{"award-number":["C2005-24Y"]}]},{"name":"RGC General Research Fund","award":["12200725"],"award-info":[{"award-number":["12200725"]}]},{"name":"Australian Research Council","award":["FT220100318"],"award-info":[{"award-number":["FT220100318"]}],"id":[{"id":"https:\/\/ror.org\/05mmh0f86","id-type":"ROR","asserted-by":"crossref"}]},{"name":"RGC Young Collaborative Research","award":["C2005-24Y"],"award-info":[{"award-number":["C2005-24Y"]}]},{"name":"RGC General Research Fund","award":["12200725"],"award-info":[{"award-number":["12200725"]}]},{"name":"JST ASPIRE","award":["JPMJAP2405"],"award-info":[{"award-number":["JPMJAP2405"]}]},{"name":"Australian Research Council","award":["FT220100318"],"award-info":[{"award-number":["FT220100318"]}],"id":[{"id":"https:\/\/ror.org\/05mmh0f86","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3693108","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:57:21Z","timestamp":1778788641000},"page":"11577-11592","source":"Crossref","is-referenced-by-count":2,"title":["Instance-Dependent Early Stopping for Adaptive Data Pruning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3747-0635","authenticated-orcid":false,"given":"Suqin","family":"Yuan","sequence":"first","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6607-7754","authenticated-orcid":false,"given":"Runqi","family":"Lin","sequence":"additional","affiliation":[{"name":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0524-0226","authenticated-orcid":false,"given":"Felix","family":"Azian","sequence":"additional","affiliation":[{"name":"Polytechnic Institute of Paris","place":["Palaiseau, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-5799","authenticated-orcid":false,"given":"Lei","family":"Feng","sequence":"additional","affiliation":[{"name":"Southeast University","place":["Nanjing, 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":"Hong Kong Baptist University","place":["Hong Kong SAR, China"]}],"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","place":["Chuo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6658-6743","authenticated-orcid":false,"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project","place":["Chuo, 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":"The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"issue":"1","key":"ref2","first-page":"335","article-title":"Early stopping and non-parametric regression: An optimal data-dependent stopping rule","volume":"15","author":"Raskutti","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"381","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"13","author":"Caruana","year":"2000"},{"key":"ref4","first-page":"21977","article-title":"Early stopping against label noise without validation data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan","year":"2024"},{"key":"ref5","first-page":"630","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"Morgan","year":"1990"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3a74"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2307\/1267351"},{"key":"ref11","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref12","article-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017"},{"key":"ref13","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1419"},{"key":"ref16","article-title":"LoftQ: LoRA-fine-tuning-aware quantization for large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2024"},{"key":"ref17","first-page":"15809","article-title":"CasCast: Skillful high-resolution precipitation nowcasting via cascaded modelling","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Gong","year":"2024"},{"key":"ref18","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rice","year":"2020"},{"key":"ref19","first-page":"10767","article-title":"Rethinking bias-variance trade-off for generalization of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2020"},{"key":"ref20","first-page":"8346","article-title":"An investigation of why overparameterization exacerbates spurious correlations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sagawa","year":"2020"},{"key":"ref21","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit","year":"2017"},{"key":"ref22","article-title":"Benign overfitting in classification: Provably counter label noise with larger models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wen","year":"2023"},{"key":"ref23","article-title":"Online batch selection for faster training of neural networks","author":"Loshchilov","year":"2015"},{"key":"ref24","article-title":"Accelerating deep learning by focusing on the biggest losers","author":"Jiang","year":"2019"},{"key":"ref25","first-page":"39723","article-title":"InfoBatch: Lossless training speed up by unbiased dynamic data pruning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Qin","year":"2024"},{"key":"ref26","first-page":"2535","article-title":"On the power of curriculum learning in training deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hacohen","year":"2019"},{"key":"ref27","first-page":"9983","article-title":"Optimizing data usage via differentiable rewards","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref28","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2017"},{"key":"ref29","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang","year":"2018"},{"key":"ref30","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.","author":"Jiang","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref32","first-page":"1567","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cao","year":"2019"},{"key":"ref33","first-page":"4604","article-title":"Do we need zero training loss after achieving zero training error?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ishida","year":"2020"},{"key":"ref34","first-page":"1024","article-title":"Sharpness minimization algorithms do not only minimize sharpness to achieve better generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wen","year":"2024"},{"key":"ref35","first-page":"43814","article-title":"On the over-memorization during natural, robust and catastrophic overfitting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2024"},{"key":"ref36","first-page":"30427","article-title":"Layer-aware analysis of catastrophic overfitting: Revealing the pseudo-robust shortcut dependency","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2968"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969154"},{"key":"ref39","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Foret","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.449"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5406"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae122"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.009"},{"key":"ref44","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref45","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref46","article-title":"Instance-dependent early stopping","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Yuan","year":"2025"},{"key":"ref47","article-title":"Variance reduction in SGD by distributed importance sampling","author":"Alain","year":"2015"},{"key":"ref48","article-title":"Biased importance sampling for deep neural network training","author":"Katharopoulos","year":"2017"},{"key":"ref49","first-page":"2525","article-title":"Not all samples are created equal: Deep learning with importance sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos","year":"2018"},{"key":"ref50","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.","volume":"30","author":"Chang","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.207"},{"key":"ref52","first-page":"5254","article-title":"Uniform convergence of rank-weighted learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Khim","year":"2020"},{"key":"ref53","article-title":"Selection via proxy: Efficient data selection for deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Coleman","year":"2020"},{"key":"ref54","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Paul","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"ref56","article-title":"Coverage-centric coreset selection for high pruning rates","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zheng","year":"2023"},{"key":"ref57","article-title":"D2 pruning: Message passing for balancing diversity and difficulty in data pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maharana","year":"2024"},{"key":"ref58","article-title":"Data pruning by information maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tan","year":"2025"},{"key":"ref59","first-page":"4087","article-title":"Coresets for scalable Bayesian logistic regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Huggins","year":"2016"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2018.00082"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS54457.2022.00051"},{"key":"ref62","article-title":"Moderate coreset: A universal method of data selection for real-world data-efficient deep learning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Xia","year":"2022"},{"key":"ref63","first-page":"54082","article-title":"Refined coreset selection: Towards minimal coreset size under model performance constraints","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Xia","year":"2024"},{"key":"ref64","first-page":"10602","article-title":"Lightweight dataset pruning without full training via example difficulty and prediction uncertainty","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Cho","year":"2025"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02477"},{"key":"ref66","article-title":"Accelerating deep learning with dynamic data pruning","author":"Raju","year":"2021"},{"key":"ref67","first-page":"15630","article-title":"Prioritized training on points that are learnable, worth learning, and not yet learnt","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mindermann","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00767"},{"key":"ref69","first-page":"37900","article-title":"KAKURENBO: Adaptively hiding samples in deep neural network training","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Truong","year":"2023"},{"issue":"27","key":"ref70","first-page":"1","article-title":"Importance sampling for minibatches","volume":"19","author":"Csiba","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","first-page":"18648","article-title":"Diversified batch selection for training acceleration","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Hong","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00037"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.acl-long.158"},{"key":"ref74","first-page":"5464","article-title":"Grad-match: Gradient matching based data subset selection for efficient deep model training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Killamsetty","year":"2021"},{"key":"ref75","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref76","article-title":"Minimal effort back propagation for convolutional neural networks","author":"Wei","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref78","article-title":"When do curricula work?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2021"},{"key":"ref79","first-page":"8602","article-title":"Curriculum learning by dynamic instance hardness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhou","year":"2020"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401036"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.26599\/CAI.2024.9390002"},{"key":"ref82","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Kumar","year":"2010"},{"key":"ref83","first-page":"5238","article-title":"Curriculum learning by transfer learning: Theory and experiments with deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weinshall","year":"2018"},{"key":"ref84","first-page":"11095","article-title":"Data parameters: A new family of parameters for learning a differentiable curriculum","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Saxena","year":"2019"},{"key":"ref85","article-title":"Active learning literature survey","volume":"42","author":"Settles","year":"2007"},{"key":"ref86","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal","year":"2017"},{"key":"ref87","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sener","year":"2018"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref89","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ash","year":"2020"},{"key":"ref90","first-page":"2101","article-title":"Stochastic modified equations and adaptive stochastic gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2017"},{"key":"ref91","article-title":"Harnessing out-of-distribution examples via augmenting content and style","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2023"},{"key":"ref92","first-page":"1","article-title":"Winning prize comes from losing tickets: Improve invariant learning by exploring variant parameters for out-of-distribution generalization","volume":"133","author":"Huang","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref93","first-page":"28965","article-title":"Towards realistic model selection for semi-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref94","first-page":"27472","article-title":"Improving non-transferable representation learning by harnessing content and style","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hong","year":"2024"},{"key":"ref95","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","volume":"87","author":"Nesterov","year":"2013"},{"key":"ref96","article-title":"Gradient descent on neural networks typically occurs at the edge of stability","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cohen","year":"2021"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref98","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Andriushchenko","year":"2022"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01552"},{"key":"ref100","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dinh","year":"2017"},{"key":"ref101","first-page":"9636","article-title":"Normalized flat minima: Exploring scale invariant definition of flat minima for neural networks using PAC-Bayesian analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tsuzuku","year":"2020"},{"key":"ref102","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Keskar","year":"2017"},{"key":"ref103","first-page":"5949","article-title":"Exploring generalization in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Neyshabur","year":"2017"},{"key":"ref104","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref107","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref108","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref110","article-title":"Caltech 101","author":"Li","year":"2022"},{"key":"ref111","article-title":"When less is more: Investigating data pruning for pretraining LLMs at scale","author":"Marion","year":"2023"},{"key":"ref112","first-page":"24058","article-title":"Repeated random sampling for minimizing the time-to-accuracy of learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Okanovic","year":"2024"},{"key":"ref113","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref114","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dao","year":"2024"},{"key":"ref115","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref116","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref117","article-title":"The PASCAL visual object classes challenge 2007 (VOC2007) results","author":"Everingham","year":"2007"},{"key":"ref118","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref119","article-title":"The PASCAL visual object classes challenge 2012 (VOC2012) Results","author":"Everingham","year":"2012"},{"issue":"2018","key":"ref120","article-title":"Large-scale celebfaces attributes (celeba) dataset","volume":"15","author":"Liu","year":"2018"},{"key":"ref121","article-title":"Fairlearn: A toolkit for assessing and improving fairness in AI","author":"Bird","year":"2020"},{"key":"ref122","first-page":"1","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia","year":"2020"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01473"},{"key":"ref124","article-title":"Learning with symmetric label noise: The importance of being unhinged","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Rooyen","year":"2015"},{"key":"ref125","first-page":"7597","article-title":"Part-dependent label noise: Towards instance-dependent label noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xia","year":"2020"},{"key":"ref126","article-title":"An empirical study of example forgetting during deep neural network learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Toneva","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11517544.pdf?arnumber=11517544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:53:36Z","timestamp":1790265216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11517544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":126,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3693108","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":[[2026,10]]}}}