{"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/unbiased-multiple-instance-learning-for","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","arxiv_id":"2303.12369","date":"2023-03-22","proceeding":"CVPR 2023 1","authors":["Hui Lv","Zhongqi Yue","Qianru Sun","Bin Luo","Zhen Cui","Hanwang Zhang"],"abstract":"Weakly Supervised Video Anomaly Detection (WSVAD) is challenging because the binary anomaly label is only given on the video level, but the output requires snippet-level predictions. So, Multiple Instance Learning (MIL) is prevailing in WSVAD. However, MIL is notoriously known to suffer from many false alarms because the snippet-level detector is easily biased towards the abnormal snippets with simple context, confused by the normality with the same bias, and missing the anomaly with a different pattern. To this end, we propose a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD. At each MIL training iteration, we use the current detector to divide the samples into two groups with different context biases: the most confident abnormal/normal snippets and the rest ambiguous ones. Then, by seeking the invariant features across the two sample groups, we can remove the variant context biases. Extensive experiments on benchmarks UCF-Crime and TAD demonstrate the effectiveness of our UMIL. Our code is provided at https://github.com/ktr-hubrt/UMIL.","url_abs":"https://arxiv.org/abs/2303.12369v1","url_pdf":"https://arxiv.org/pdf/2303.12369v1.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":"unbiased-multiple-instance-learning-for","repo_url":"https://github.com/ktr-hubrt/umil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"},{"task_slug":"weakly-supervised-video-anomaly-detection","task_name":"Weakly-supervised Video Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-video-anomaly-detection-on","task":"Weakly-supervised Video Anomaly Detection","dataset":"ShanghaiTech Weakly Supervised","model":"UML","rank_in_archive_order":11,"of":16,"metrics":{"AUC-ROC":"96.78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.12369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12369"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ktr-hubrt/umil","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ktr-hubrt/UMIL","reach":{"status":"ok"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"6072be06bdb2c959","entry":"MultiframeIntegrationTransformer","repo":"ktr-hubrt/UMIL","repo_kind":"official","path":"models/mit.py","file_url":"https://github.com/ktr-hubrt/UMIL/blob/HEAD/models/mit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6072be06bdb2c959"}},{"code_sha256_prefix":"99145f709504d6ad","entry":"ResidualAttentionBlock","repo":"ktr-hubrt/UMIL","repo_kind":"official","path":"models/mit.py","file_url":"https://github.com/ktr-hubrt/UMIL/blob/HEAD/models/mit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99145f709504d6ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}