{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:53:02Z","timestamp":1778860382030,"version":"3.51.4"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["2022YFC3400404"],"award-info":[{"award-number":["2022YFC3400404"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971165"],"award-info":[{"award-number":["61971165"]}],"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":["61922027"],"award-info":[{"award-number":["61922027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tnnls.2022.3222044","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T16:39:20Z","timestamp":1669307960000},"page":"7899-7910","source":"Crossref","is-referenced-by-count":6,"title":["ReSmooth: Detecting and Utilizing OOD Samples When Training With Data Augmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8706-5354","authenticated-orcid":false,"given":"Chenyang","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5694-505X","authenticated-orcid":false,"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0856-6696","authenticated-orcid":false,"given":"Xiong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8857-1785","authenticated-orcid":false,"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improved regularization of convolutional neural networks with cutout","volume-title":"arXiv:1708.04552","author":"DeVries","year":"2017"},{"key":"ref2","article-title":"AutoAugment: Learning augmentation policies from data","volume-title":"arXiv:1805.09501","author":"Cubuk","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3152245"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071275"},{"key":"ref8","volume-title":"Detectron","author":"Girshick","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00077"},{"key":"ref10","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref11","first-page":"3239","article-title":"Learning to compose domain-specific transformations for data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Ratner"},{"key":"ref12","article-title":"Affinity and diversity: Quantifying mechanisms of data augmentation","volume-title":"arXiv:2002.08973","author":"Gontijo-Lopes","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_36"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00111"},{"key":"ref15","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"arXiv:1803.07728","author":"Gidaris","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref17","article-title":"Negative data augmentation","volume-title":"arXiv:2102.05113","author":"Sinha","year":"2021"},{"key":"ref18","first-page":"2731","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","volume-title":"Proc. ICML","author":"Ho"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01633"},{"key":"ref20","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"arXiv:1912.02781","author":"Hendrycks","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01063"},{"key":"ref22","first-page":"6665","article-title":"Fast AutoAugment","volume-title":"Proc. NIPS","volume":"32","author":"Lim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref24","article-title":"Generalized out-of-distribution detection: A survey","volume-title":"arXiv:2110.11334","author":"Yang","year":"2021"},{"key":"ref25","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"arXiv:1610.02136","author":"Hendrycks","year":"2016"},{"key":"ref26","first-page":"1","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. NeurIPS","volume":"31","author":"Lee"},{"key":"ref27","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref28","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"arXiv:2002.07394","author":"Li","year":"2020"},{"key":"ref29","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. ICML","author":"Arazo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"ref31","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"arXiv:1804.06872","author":"Han","year":"2018"},{"key":"ref32","article-title":"Decoupling \u2018when to update\u2019 from \u2018how to update","volume-title":"arXiv:1706.02613","author":"Malach","year":"2017"},{"key":"ref33","article-title":"Identifying mislabeled data using the area under the margin ranking","volume-title":"arXiv:2001.10528","author":"Pleiss","year":"2020"},{"key":"ref34","article-title":"What do compressed deep neural networks forget?","volume-title":"arXiv:1911.05248","author":"Hooker","year":"2019"},{"key":"ref35","article-title":"Self-damaging contrastive learning","volume-title":"arXiv:2106.02990","author":"Jiang","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"ref37","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"arXiv:2001.07685","author":"Sohn","year":"2020"},{"key":"ref38","article-title":"Does data augmentation benefit from split BatchNorms","volume-title":"arXiv:2010.07810","author":"Merchant","year":"2020"},{"key":"ref39","article-title":"Reweighting augmented samples by minimizing the maximal expected loss","volume-title":"arXiv:2103.08933","author":"Yi","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2005.10.028"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref42","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01619"},{"key":"ref48","first-page":"1","article-title":"When does label smoothing help?","volume-title":"Proc. NeurIPS","volume":"32","author":"M\u00fcller"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10547160\/09961105.pdf?arnumber=9961105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T18:43:17Z","timestamp":1719340997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9961105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3222044","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}