{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:30:08Z","timestamp":1775068208697,"version":"3.50.1"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["LP230201022"],"award-info":[{"award-number":["LP230201022"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP240102050"],"award-info":[{"award-number":["DP240102050"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["LE240100131"],"award-info":[{"award-number":["LE240100131"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1016\/j.artint.2024.104275","type":"journal-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T16:27:35Z","timestamp":1734107255000},"page":"104275","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Out-of-distribution detection by regaining lost clues"],"prefix":"10.1016","volume":"339","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6391-8423","authenticated-orcid":false,"given":"Zhilin","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-9429","authenticated-orcid":false,"given":"Longbing","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.artint.2024.104275_br0010","series-title":"SIGKDD","first-page":"4774","article-title":"Shallow and deep non-iid learning on complex data","author":"Cao","year":"2022"},{"key":"10.1016\/j.artint.2024.104275_br0020","series-title":"CoRR","first-page":"1","article-title":"A unified survey on anomaly, novelty, open-set, and out-of-distribution detection: solutions and future challenges","author":"Salehi","year":"2021"},{"issue":"7","key":"10.1016\/j.artint.2024.104275_br0030","first-page":"8888","article-title":"Revealing the distributional vulnerability of discriminators by implicit generators","volume":"45","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.artint.2024.104275_br0040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNNLS.2023.3341841","article-title":"Out-of-distribution detection by cross-class vicinity distribution of in-distribution data","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.artint.2024.104275_br0050","series-title":"NeurIPS","first-page":"1","article-title":"Energy-based out-of-distribution detection","author":"Liu","year":"2020"},{"key":"10.1016\/j.artint.2024.104275_br0060","first-page":"1","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"CoRR"},{"key":"10.1016\/j.artint.2024.104275_br0070","series-title":"ICLR","first-page":"1","article-title":"On the information bottleneck theory of deep learning","author":"Saxe","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0080","first-page":"1","article-title":"Dual representation learning for out-of-distribution detection","author":"Zhao","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2024.104275_br0090","series-title":"NeurIPS","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.artint.2024.104275_br0100","first-page":"1","article-title":"Human-centric transformer for domain adaptive action recognition","author":"Lin","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.artint.2024.104275_br0110","series-title":"AAAI","first-page":"5216","article-title":"Self-supervised learning for generalizable out-of-distribution detection","author":"Mohseni","year":"2020"},{"key":"10.1016\/j.artint.2024.104275_br0120","series-title":"Proceedings of NAACL-HLT","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.artint.2024.104275_br0130","series-title":"ICLR","first-page":"1","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.artint.2024.104275_br0140","series-title":"CoRR","first-page":"1","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021"},{"key":"10.1016\/j.artint.2024.104275_br0150","series-title":"ICLR","first-page":"1","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","author":"Serr\u00e0","year":"2020"},{"issue":"9","key":"10.1016\/j.artint.2024.104275_br0160","doi-asserted-by":"crossref","first-page":"4052","DOI":"10.1109\/TKDE.2020.3036524","article-title":"A novel outlier detection method for multivariate data","volume":"34","author":"Almardeny","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.artint.2024.104275_br0170","series-title":"NeurIPS","first-page":"1","article-title":"Diversifying spatial-temporal perception for video domain generalization","author":"Lin","year":"2023"},{"issue":"15","key":"10.1016\/j.artint.2024.104275_br0180","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1016\/j.artint.2010.07.006","article-title":"Outlier detection for simple default theories","volume":"174","author":"Angiulli","year":"2010","journal-title":"Artif. Intell."},{"key":"10.1016\/j.artint.2024.104275_br0190","series-title":"ICLR","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2017"},{"key":"10.1016\/j.artint.2024.104275_br0200","series-title":"NeurIPS","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"Lee","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0210","series-title":"NeurIPS","first-page":"10622","article-title":"Deep gamblers: learning to abstain with portfolio theory","author":"Liu","year":"2019"},{"key":"10.1016\/j.artint.2024.104275_br0220","series-title":"ICLR","first-page":"1","article-title":"Deep anomaly detection with outlier exposure","author":"Hendrycks","year":"2019"},{"key":"10.1016\/j.artint.2024.104275_br0230","series-title":"NeurIPS","first-page":"144","article-title":"ReAct: out-of-distribution detection with rectified activations","author":"Sun","year":"2021"},{"key":"10.1016\/j.artint.2024.104275_br0240","series-title":"ICML","first-page":"4390","article-title":"Deep one-class classification","author":"Ruff","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0250","series-title":"NeurIPS","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Guyon","year":"2017"},{"key":"10.1016\/j.artint.2024.104275_br0260","series-title":"ICLR","first-page":"1","article-title":"On mutual information maximization for representation learning","author":"Tschannen","year":"2020"},{"key":"10.1016\/j.artint.2024.104275_br0270","series-title":"Understanding Machine Learning from Theory to Algorithms","author":"Shalev-Shwartz","year":"2014"},{"key":"10.1016\/j.artint.2024.104275_br0280","series-title":"Foundations of Machine Learning","author":"Mohri","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0290","series-title":"Convex Optimization","author":"Boyd","year":"2004"},{"key":"10.1016\/j.artint.2024.104275_br0300","series-title":"COLT","first-page":"297","article-title":"Size-independent sample complexity","volume":"vol. 75","author":"Golowich","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0310","series-title":"CVPR","first-page":"8710","article-title":"MOS: towards scaling out-of-distribution detection for large semantic space","author":"Huang","year":"2021"},{"key":"10.1016\/j.artint.2024.104275_br0320","series-title":"NeurIPS","first-page":"7386","article-title":"Out-of-distribution detection using multiple semantic label representations","author":"Shalev","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0330","series-title":"ICLR","first-page":"1","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"Liang","year":"2018"},{"key":"10.1016\/j.artint.2024.104275_br0340","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.artint.2024.104275_br0350","series-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"},{"key":"10.1016\/j.artint.2024.104275_br0360","author":"Yu"},{"key":"10.1016\/j.artint.2024.104275_br0370","series-title":"CVPR","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S000437022400211X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S000437022400211X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:48:28Z","timestamp":1737398908000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S000437022400211X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":37,"alternative-id":["S000437022400211X"],"URL":"https:\/\/doi.org\/10.1016\/j.artint.2024.104275","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Out-of-distribution detection by regaining lost clues","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artint.2024.104275","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104275"}}