{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T10:43:14Z","timestamp":1767868994410,"version":"3.49.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62473286"],"award-info":[{"award-number":["62473286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["22ZR1466700"],"award-info":[{"award-number":["22ZR1466700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076184"],"award-info":[{"award-number":["62076184"]}],"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":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3594149","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T18:31:16Z","timestamp":1753986676000},"page":"10262-10279","source":"Crossref","is-referenced-by-count":1,"title":["DPL++: Advancing the Network Performance via Image and Label Perturbations"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8734-9878","authenticated-orcid":false,"given":"Zifan","family":"Song","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0345-5986","authenticated-orcid":false,"given":"Xiao","family":"Gong","sequence":"additional","affiliation":[{"name":"Shining3D Technology Company, Ltd., Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9448-9892","authenticated-orcid":false,"given":"Guosheng","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3231-8817","authenticated-orcid":false,"given":"Shuguang","family":"Dou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7120-8170","authenticated-orcid":false,"given":"Qingsong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-9674","authenticated-orcid":false,"given":"Cairong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"32","article-title":"Deep perturbation learning: Enhancing the network performance via image perturbations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089942"},{"key":"ref4","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref6","article-title":"Robustness may be at odds with accuracy","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Tsipras"},{"key":"ref7","first-page":"4016","article-title":"Max-mahalanobis linear discriminant analysis networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pang"},{"key":"ref8","article-title":"Rethinking softmax cross-entropy loss for adversarial robustness","author":"Pang","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref10","first-page":"3358","article-title":"Adversarial training for free","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shafahi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01635"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw50498.2020.00359"},{"key":"ref16","article-title":"Adversarial AutoAugment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref17","first-page":"2731","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ho"},{"key":"ref18","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref19","volume-title":"Robust Statistics: The Approach Based on Influence Functions","volume":"196","author":"Hampel","year":"2011"},{"key":"ref20","article-title":"Estimating training data influence by tracing gradient descent","author":"Pruthi","year":"2020"},{"key":"ref21","article-title":"Understanding instance-based interpretability of variational auto-encoders","author":"Kong","year":"2021"},{"key":"ref22","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2014"},{"key":"ref23","first-page":"6448","article-title":"Does label smoothing mitigate label noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lukasik"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.514"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01909"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02080-0"},{"key":"ref29","article-title":"Unveiling the backbone-optimizer coupling bias in visual representation learning","author":"Li","year":"2024"},{"key":"ref30","article-title":"Architecture-agnostic masked image modeling\u2013from vit back to cnn","author":"Li","year":"2022"},{"key":"ref31","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref33","first-page":"2890","article-title":"Revisiting label smoothing and knowledge distillation compatibility: What was missing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chandrasegaran"},{"key":"ref34","article-title":"Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective","author":"Zhou","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01576"},{"key":"ref37","article-title":"ActPrompt: In-domain feature adaptation via action cues for video temporal grounding","author":"Wang","year":"2024"},{"key":"ref38","volume-title":"Calculus of Variations","author":"Gelfand","year":"2000"},{"key":"ref39","first-page":"125","article-title":"Adversarial examples are not bugs, they are features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ilyas"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref45","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref46","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref52","first-page":"20149","article-title":"Architecture-agnostic masked image modeling\u2013from ViT back to CNN","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref53","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.1.147"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref57","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref60","article-title":"Fast AdvProp","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mei"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref66","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357369"},{"key":"ref68","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref69","article-title":"Adversarial active learning for deep networks: A margin based approach","author":"Ducoffe","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"ref72","first-page":"321","article-title":"Learning with local and global consistency","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390297"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref75","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref76","first-page":"244","article-title":"On the optimization of deep networks: Implicit acceleration by overparameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arora"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref78","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref80","first-page":"6665","article-title":"Fast AutoAugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref81","article-title":"Deep AutoAugment","author":"Zheng","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11106184.pdf?arnumber=11106184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:40Z","timestamp":1759772200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11106184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":81,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3594149","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":[[2025,11]]}}}