{"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/learning-to-generalize-without-bias-for-open","title":"Learning to Generalize without Bias for Open-Vocabulary Action Recognition","arxiv_id":"2502.20158","date":"2025-02-27","proceeding":null,"authors":["Yating Yu","Congqi Cao","Yifan Zhang","Yanning Zhang"],"abstract":"Leveraging the effective visual-text alignment and static generalizability from CLIP, recent video learners adopt CLIP initialization with further regularization or recombination for generalization in open-vocabulary action recognition in-context. However, due to the static bias of CLIP, such video learners tend to overfit on shortcut static features, thereby compromising their generalizability, especially to novel out-of-context actions. To address this issue, we introduce Open-MeDe, a novel Meta-optimization framework with static Debiasing for Open-vocabulary action recognition. From a fresh perspective of generalization, Open-MeDe adopts a meta-learning approach to improve known-to-open generalizing and image-to-video debiasing in a cost-effective manner. Specifically, Open-MeDe introduces a cross-batch meta-optimization scheme that explicitly encourages video learners to quickly generalize to arbitrary subsequent data via virtual evaluation, steering a smoother optimization landscape. In effect, the free of CLIP regularization during optimization implicitly mitigates the inherent static bias of the video meta-learner. We further apply self-ensemble over the optimization trajectory to obtain generic optimal parameters that can achieve robust generalization to both in-context and out-of-context novel data. Extensive evaluations show that Open-MeDe not only surpasses state-of-the-art regularization methods tailored for in-context open-vocabulary action recognition but also substantially excels in out-of-context scenarios.","url_abs":"https://arxiv.org/abs/2502.20158v1","url_pdf":"https://arxiv.org/pdf/2502.20158v1.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":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"open-vocabulary-action-recognition","task_name":"Open Vocabulary Action Recognition"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.20158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20158"}},"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":"deterministic:regex_extraction","url":"https://github.com/Mia-YatingYu/Open-MeDe","reach":null}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":7,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"54f78e361cbab192","entry":"CrossFramelAttentionBlock","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"54f78e361cbab192"}},{"code_sha256_prefix":"b84374673409547e","entry":"ResidualAttentionBlock","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b84374673409547e"}},{"code_sha256_prefix":"3740fcc18a01e4e9","entry":"STAdaptZeroInitAttentionBlock","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3740fcc18a01e4e9"}},{"code_sha256_prefix":"12a3c3d58e8ae833","entry":"STCrossAttentionBlock","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12a3c3d58e8ae833"}},{"code_sha256_prefix":"d1e07d070c924b50","entry":"ChannelShiftAttentionBlock","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1e07d070c924b50"}},{"code_sha256_prefix":"0ffb06ad1d4b5b8d","entry":"TSTransformer","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ffb06ad1d4b5b8d"}},{"code_sha256_prefix":"3cf27c4868cfc5d1","entry":"TimesAttentionBlock","repo":"Mia-YatingYu/Open-MeDe","repo_kind":"found_in_text","path":"slowfast/models/customize_visiontransformer.py","file_url":"https://github.com/Mia-YatingYu/Open-MeDe/blob/HEAD/slowfast/models/customize_visiontransformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3cf27c4868cfc5d1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}