{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rethinking-out-of-distribution-ood-detection","title":"Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need","arxiv_id":"2302.02615","date":"2023-02-06","proceeding":"CVPR 2023 1","authors":["Jingyao Li","Pengguang Chen","Shaozuo Yu","Zexin He","Shu Liu","Jiaya Jia"],"abstract":"The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, which tend to learn shortcuts instead of comprehensive representations. In this work, we find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We deeply explore the main contributors of OOD detection and find that reconstruction-based pretext tasks have the potential to provide a generally applicable and efficacious prior, which benefits the model in learning intrinsic data distributions of the ID dataset. Specifically, we take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD). Without bells and whistles, MOOD outperforms previous SOTA of one-class OOD detection by 5.7%, multi-class OOD detection by 3.0%, and near-distribution OOD detection by 2.1%. It even defeats the 10-shot-per-class outlier exposure OOD detection, although we do not include any OOD samples for our detection","url_abs":"https://arxiv.org/abs/2302.02615v2","url_pdf":"https://arxiv.org/pdf/2302.02615v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rethinking-out-of-distribution-ood-detection","repo_url":"https://github.com/julietljy/mood","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"rethinking-out-of-distribution-ood-detection","repo_url":"https://github.com/dvlab-research/mood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-12","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Curated OODs (avg.)","model":"MOOD","rank_in_archive_order":16,"of":16,"metrics":{"AUROC":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-9","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Places","model":"MOOD","rank_in_archive_order":25,"of":25,"metrics":{"AUROC":"88.5"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-8","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs SUN","model":"MOOD","rank_in_archive_order":22,"of":22,"metrics":{"AUROC":"89.8"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-10","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Textures","model":"MOOD","rank_in_archive_order":18,"of":34,"metrics":{"AUROC":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-3","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs iNaturalist","model":"MOOD","rank_in_archive_order":21,"of":28,"metrics":{"AUROC":"86.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.02615","atlas_url":"https://app.syntology.ai/?focus=2302.02615","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}