{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:36Z","timestamp":1783455456719,"version":"3.55.0"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476214"],"award-info":[{"award-number":["62476214"]}],"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":["U24A20324"],"award-info":[{"award-number":["U24A20324"]}],"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":["12326606"],"award-info":[{"award-number":["12326606"]}],"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":["32430017"],"award-info":[{"award-number":["32430017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM101"],"award-info":[{"award-number":["JYB2025XDXM101"]}]},{"name":"Tianyuan Fund for Mathematics of the National Natural Science Foundation of China"},{"name":"Tianyuan Fund for Mathematics of the National Natural Science Foundation of China","award":["12426105"],"award-info":[{"award-number":["12426105"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3680442","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:53:17Z","timestamp":1775245997000},"page":"9642-9658","source":"Crossref","is-referenced-by-count":0,"title":["DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning"],"prefix":"10.1109","volume":"48","author":[{"given":"Jun","family":"Shu","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’An, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2687-8943","authenticated-orcid":false,"given":"Xiang","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’An, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1294-8283","authenticated-orcid":false,"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4066-2338","authenticated-orcid":false,"given":"Zongben","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics and Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’An, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.287172"},{"key":"ref7","article-title":"Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta-$\\cdots$\u22ef hook","author":"Schmidhuber","year":"1987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"issue":"186","key":"ref10","first-page":"1","article-title":"Learning an explicit hyper-parameter prediction function conditioned on tasks","volume":"24","author":"Shu","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref12","article-title":"Small sample learning in Big Data era","author":"Shu","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3470918"},{"issue":"81","key":"ref15","first-page":"1","article-title":"The benefit of multitask representation learning","volume":"17","author":"Maurer","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","first-page":"7852","article-title":"On the theory of transfer learning: The importance of task diversity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tripuraneni"},{"key":"ref17","first-page":"1919","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref18","first-page":"22968","article-title":"Cycle self-training for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref19","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref20","first-page":"23664","article-title":"Adaptive risk minimization: Learning to adapt to domain shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref21","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00020"},{"key":"ref23","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref24","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref26","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Laine"},{"key":"ref27","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref30","first-page":"1","article-title":"Adamatch: A unified approach to semi-supervised learning and domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Berthelot"},{"key":"ref31","first-page":"11190","article-title":"Unlabeled data improves adversarial robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Carmon"},{"key":"ref32","first-page":"12214","article-title":"Are labels required for improving adversarial robustness?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref33","first-page":"1","article-title":"Consistency regularization for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref34","first-page":"12943","article-title":"Consistency regularization for variational auto-encoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sinha"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00685"},{"key":"ref36","first-page":"1","article-title":"Meta-learning without memorization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yin"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"ref38","first-page":"5705","article-title":"Meta-learning requires meta-augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rajendran"},{"key":"ref39","article-title":"Task augmentation by rotating for meta-learning","author":"Liu","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413158"},{"key":"ref41","first-page":"11887","article-title":"Improving generalization in meta-learning via task augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1190"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2008"},{"key":"ref44","article-title":"Meta-task: A method-agnostic framework for learning to regularize in few-shot learning","author":"Rostami","year":"2024"},{"key":"ref45","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae277"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3079836"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2020.101656"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1126\/science.1201765"},{"issue":"3","key":"ref50","article-title":"Natural-born cyborgs: Minds, technologies, and the future of human intelligence","volume":"29","author":"Clark","year":"2004","journal-title":"Can. J. Sociol."},{"issue":"Nov","key":"ref51","first-page":"463","article-title":"Rademacher and gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref53","article-title":"Meta-learning with differentiable closed-form solvers","volume-title":"Int. Conf. Learn. Representations","author":"Bertinetto"},{"key":"ref54","first-page":"1","article-title":"Meta dropout: Learning to perturb latent features for generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref55","first-page":"1170","article-title":"A theory of label propagation for subpopulation shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai"},{"key":"ref56","first-page":"1","article-title":"Theoretical analysis of self-training with deep networks on unlabeled data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00702"},{"key":"ref59","first-page":"1","article-title":"Distributionally robust neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref61","first-page":"7404","article-title":"Bridging theory and algorithm for domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref62","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schneider"},{"key":"ref63","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref64","first-page":"11588","article-title":"Look-ahead meta learning for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref66","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref67","article-title":"Efficient lifelong learning with a-gem","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry"},{"key":"ref68","first-page":"1","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Riemer"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00673"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"ref72","first-page":"1","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Triantafillou"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00863"},{"key":"ref74","first-page":"2825","article-title":"Explicit inductive bias for transfer learning with convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xuhong"},{"key":"ref75","first-page":"1","article-title":"DELTA: Deep learning transfer using feature map with attention for convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref76","first-page":"17236","article-title":"Co-tuning for transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref79","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00793"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.240"},{"key":"ref82","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00718"},{"key":"ref84","first-page":"1","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00046"},{"key":"ref86","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"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref88","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref89","first-page":"6838","article-title":"Are anchor points really indispensable in label-noise learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xia"},{"key":"ref90","first-page":"7260","article-title":"Dual T: Reducing estimation error for transition matrix in label-noise learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref91","first-page":"6403","article-title":"Provably end-to-end label-noise learning without anchor points","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref92","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref93","article-title":"Meta transition adaptation for robust deep learning with noisy labels","author":"Shu","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11474500.pdf?arnumber=11474500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:35Z","timestamp":1783453475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11474500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":93,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3680442","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":[[2026,8]]}}}