{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:01:55Z","timestamp":1775278915061,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Vanderbilt-Liverpool Seed","award":["20252026"],"award-info":[{"award-number":["20252026"]}]},{"name":"EPSRC AISI's, The Alignment Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2025.3650695","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:38:31Z","timestamp":1767638311000},"page":"5243-5260","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting Out-of-Distribution Detection in Real-Time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8293-2888","authenticated-orcid":false,"given":"Changshun","family":"Wu","sequence":"first","affiliation":[{"name":"Université Grenoble Alpes, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2507-4256","authenticated-orcid":false,"given":"Weicheng","family":"He","sequence":"additional","affiliation":[{"name":"Université Grenoble Alpes, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7265-8413","authenticated-orcid":false,"given":"Chih-Hong","family":"Cheng","sequence":"additional","affiliation":[{"name":"Carl von Ossietzky University of Oldenburg, Oldenburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6267-0366","authenticated-orcid":false,"given":"Xiaowei","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5753-2126","authenticated-orcid":false,"given":"Saddek","family":"Bensalem","sequence":"additional","affiliation":[{"name":"CSX-AI, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VOS: Learning what you don\u2019t know by virtual outlier synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02154"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801584"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-74234-7_15"},{"key":"ref6","first-page":"107984","article-title":"YOLOv 10: Real-time end-to-end object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wang","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref8","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":"ref9","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu","year":"2020"},{"key":"ref10","first-page":"16316","article-title":"Scaling for training time and post-hoc out-of-distribution detection enhancement","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2024"},{"key":"ref11","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2018","author":"Lee"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714971"},{"key":"ref13","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44267-4_2"},{"key":"ref15","article-title":"Likelihood ratios for out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren","year":"2019"},{"key":"ref16","first-page":"22908","article-title":"A geometric explanation of the likelihood OOD detection paradox","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kamkari","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref18","first-page":"32598","article-title":"OpenOOD: Benchmarking generalized out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yang","year":"2022"},{"key":"ref19","first-page":"8759","article-title":"Scaling out-of-distribution detection for real-world settings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hendrycks","year":"2022"},{"key":"ref20","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2017"},{"key":"ref21","article-title":"Adversarial training and robustness for multiple perturbations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2019","author":"Tramer"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11245852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00271"},{"key":"ref27","article-title":"Fiftyone","author":"Moore","year":"2020"},{"key":"ref28","first-page":"24591","article-title":"YOLOE: Real-time seeing anything","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wang","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19894"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0068"},{"key":"ref31","article-title":"Ultralytics\/yolov5: V7. 0-yolov5 sota realtime instance segmentation","author":"Jocher","year":"2023"},{"key":"ref32","first-page":"350","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rolnick","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00912"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref41","article-title":"Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geirhos","year":"2019"},{"key":"ref42","first-page":"7068","article-title":"Exploring the limits of out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fort","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00276"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11328890.pdf?arnumber=11328890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T04:17:48Z","timestamp":1775276268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11328890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":43,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3650695","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":[[2026,5]]}}}