{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:07:31Z","timestamp":1770739651022,"version":"3.49.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["624B2106"],"award-info":[{"award-number":["624B2106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program of Hubei Province","award":["2024BAB038"],"award-info":[{"award-number":["2024BAB038"]}]},{"name":"National Key R&D Program of China","award":["2023YFC3604702"],"award-info":[{"award-number":["2023YFC3604702"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042025kf0045"],"award-info":[{"award-number":["2042025kf0045"]}],"id":[{"id":"10.13039\/501100012226","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":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3642151","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:32:53Z","timestamp":1765305173000},"page":"3544-3555","source":"Crossref","is-referenced-by-count":1,"title":["A Unified Decision Rule for Generalized Out-of-Distribution Detection"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1652-4730","authenticated-orcid":false,"given":"Xinsong","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7277-6703","authenticated-orcid":false,"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1130-1792","authenticated-orcid":false,"given":"Xin","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-3369","authenticated-orcid":false,"given":"Weiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref2","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01321"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref5","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":"ref6","article-title":"Theoretical investigation on inductive bias of isolation forest","author":"Zheng","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"ref8","first-page":"1237","article-title":"Anomaly detection using deep learning based image completion","volume-title":"Proc. 17th IEEE Int. Conf. Mach. Learn. Appl.","author":"Gruber","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5220\/0007364500002108"},{"key":"ref11","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"2022","author":"Sun"},{"key":"ref12","first-page":"23631","article-title":"Mitigating neural network overconfidence with logit normalization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Wei","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013699998"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/08-EJS180"},{"key":"ref16","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Hendrycks","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01169"},{"key":"ref18","first-page":"8759","article-title":"Scaling out-of-distribution detection for real-world settings","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"2022","author":"Hendrycks"},{"key":"ref19","article-title":"Extremely simple activation shaping for out-of-distribution detection","volume-title":"Proc. Eleventh Int. Conf. Learn. Representations","author":"Djurisic","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02293"},{"key":"ref21","first-page":"60878","article-title":"Dream the impossible: Outlier imagination with diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du","year":"2023"},{"key":"ref22","first-page":"12427","article-title":"Understanding failures in out-of-distribution detection with deep generative models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Zhang","year":"2021"},{"key":"ref23","first-page":"37199","article-title":"Is out-of-distribution detection learnable","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2022","author":"Fang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00189"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref27","first-page":"40290","article-title":"Delving into noisy label detection with clean data","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"2023","author":"Yu"},{"key":"ref28","first-page":"34094","article-title":"A provable decision rule for out-of-distribution detection","volume-title":"Proc. Forty-first Int. Conf. Mach. Learn.","author":"Ma","year":"2024"},{"key":"ref29","article-title":"A closer look at generalized BH algorithm for out-of-distribution detection","volume-title":"Proc. Forty-second Int. Conf. Mach. Learn.","author":"Ma","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107147"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOS557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1765"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000265"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5705\/ss.2014.138"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00346"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOS667"},{"key":"ref38","volume-title":"Statistical Inference.","author":"Casella","year":"2002"},{"key":"ref39","first-page":"17885","article-title":"Rankfeat: Rank-1 feature removal for out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2022"},{"key":"ref40","article-title":"How to exploit hyperspherical embeddings for out-of-distribution detection?","volume-title":"Proc. Eleventh Int. Conf. Learn. Representations","author":"Ming","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00162"},{"key":"ref42","article-title":"Out-of-distribution detection based on in-distribution data patterns memorization with modern hopfield energy","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref43","article-title":"Scaling for training time and post-hoc out-of-distribution detection enhancement","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Xu","year":"2024"},{"key":"ref44","first-page":"31728","article-title":"Fast decision boundary based out-of-distribution detector","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01437"},{"key":"ref46","article-title":"Improving out-of-distribution detection via dynamic covariance calibration","volume-title":"Proc. Forty-Second Int. Conf. Mach. Learn.","author":"Guo","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref48","first-page":"28941","article-title":"VRA: Variational rectified activation for out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2023"},{"key":"ref49","article-title":"Towards optimal feature-shaping methods for out-of-distribution detection","volume-title":"Proc. Twelfth Int. Conf. Learn. Representations","author":"Zhao","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1395"},{"key":"ref51","first-page":"72840","article-title":"Setar: Out-of-distribution detection with selective low-rank approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193699"},{"key":"ref53","article-title":"FastFlow: Unsupervised Anomaly Detection and Localization Via 2D Normalizing Flows","author":"Yu","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"ref58","article-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref62","article-title":"Reading Digits in Natural Images With Unsupervised Feature Learning","author":"Netzer","year":"2011","journal-title":"NeurIPS Workshop"},{"key":"ref63","article-title":"Kylberg texture dataset v. 1.0. centre for image analysis","author":"Kylberg","year":"2011","journal-title":"Swedish Univ. Agricultural Sci. Uppsala Univ."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref65","article-title":"Open-set recognition: A good closed-set classifier is all you need","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vaze","year":"2022"},{"key":"ref66","first-page":"2471","article-title":"In or out? fixing imagenet out-of-distribution detection evaluation","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Bitterwolf","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_23"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"ref73","first-page":"32598","article-title":"Openood: Benchmarking generalized out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2022"},{"key":"ref74","article-title":"Openood v1.5: Enhanced benchmark for out-of-distribution detection","author":"Zhang","year":"2023","journal-title":"NeurIPS Workshop"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref76","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"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11288088.pdf?arnumber=11288088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:48Z","timestamp":1770671148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11288088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":76,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3642151","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":[[2026,3]]}}}