{"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/dpu-dynamic-prototype-updating-for-multimodal","title":"DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection","arxiv_id":"2411.08227","date":"2024-11-12","proceeding":"CVPR 2025 1","authors":["Shawn Li","Huixian Gong","Hao Dong","Tiankai Yang","Zhengzhong Tu","Yue Zhao"],"abstract":"Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution. While traditional OOD detection has primarily focused on single-modality inputs, such as images, recent advances in multimodal models have demonstrated the potential of leveraging multiple modalities (e.g., video, optical flow, audio) to enhance detection performance. However, existing methods often overlook intra-class variability within in-distribution (ID) data, assuming that samples of the same class are perfectly cohesive and consistent. This assumption can lead to performance degradation, especially when prediction discrepancies are uniformly amplified across all samples. To address this issue, we propose Dynamic Prototype Updating (DPU), a novel plug-and-play framework for multimodal OOD detection that accounts for intra-class variations. Our method dynamically updates class center representations for each class by measuring the variance of similar samples within each batch, enabling adaptive adjustments. This approach allows us to amplify prediction discrepancies based on the updated class centers, thereby improving the model's robustness and generalization across different modalities. Extensive experiments on two tasks, five datasets, and nine base OOD algorithms demonstrate that DPU significantly improves OOD detection performance, setting a new state-of-the-art in multimodal OOD detection, with improvements of up to 80 percent in Far-OOD detection. To facilitate accessibility and reproducibility, our code is publicly available on GitHub.","url_abs":"https://arxiv.org/abs/2411.08227v1","url_pdf":"https://arxiv.org/pdf/2411.08227v1.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":"dpu-dynamic-prototype-updating-for-multimodal","repo_url":"https://github.com/lili0415/dpu-ood-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dpu-dynamic-prototype-updating-for-multimodal","repo_url":"https://github.com/donghao51/multiood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.08227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08227"}},"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/donghao51/multiood","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lili0415/dpu-ood-detection","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":4,"samples":[{"code_sha256_prefix":"2a70efefd5fd3fdf","entry":"normalized_prediction_entropy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2a70efefd5fd3fdf"}},{"code_sha256_prefix":"e5d31e759577909d","entry":"hellinger_distance","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e5d31e759577909d"}},{"code_sha256_prefix":"5710019a55c8a04e","entry":"wasserstein_distance","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5710019a55c8a04e"}},{"code_sha256_prefix":"c157c58abd3d1ba1","entry":"generalized_entropy","repo":"lili0415/dpu-ood-detection","repo_kind":"official","path":"eval_video_flow_far_ood.py","file_url":"https://github.com/lili0415/dpu-ood-detection/blob/HEAD/eval_video_flow_far_ood.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c157c58abd3d1ba1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}