{"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/discovering-global-false-negatives-on-the-fly","title":"Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning","arxiv_id":"2502.20612","date":"2025-02-28","proceeding":null,"authors":["Vicente Balmaseda","Bokun Wang","Ching-Long Lin","Tianbao Yang"],"abstract":"In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, excluding the anchor. However, this approach can result in the creation of negative pairs with similar semantics, referred to as \"false negatives\", leading to their embeddings being falsely pushed apart. To address this issue, we introduce GloFND, an optimization-based approach that automatically learns on the fly the threshold for each anchor data to identify its false negatives during training. In contrast to previous methods for false negative discovery, our approach globally detects false negatives across the entire dataset rather than locally within the mini-batch. Moreover, its per-iteration computation cost remains independent of the dataset size. Experimental results on image and image-text data demonstrate the effectiveness of the proposed method. Our implementation is available at https://github.com/vibalcam/GloFND.","url_abs":"https://arxiv.org/abs/2502.20612v2","url_pdf":"https://arxiv.org/pdf/2502.20612v2.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":"discovering-global-false-negatives-on-the-fly","repo_url":"https://github.com/vibalcam/glofnd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.20612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20612"}},"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/vibalcam/glofnd","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"dbec5545cf79687b","entry":"FastCLIPLoss","repo":"vibalcam/glofnd","repo_kind":"official","path":"bimodal/src/fast_clip/loss.py","file_url":"https://github.com/vibalcam/glofnd/blob/HEAD/bimodal/src/fast_clip/loss.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":"dbec5545cf79687b"}},{"code_sha256_prefix":"bfb0c0121a1efcf9","entry":"FastCLIPLossGloFND","repo":"vibalcam/glofnd","repo_kind":"official","path":"bimodal/src/fast_clip/loss.py","file_url":"https://github.com/vibalcam/glofnd/blob/HEAD/bimodal/src/fast_clip/loss.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":"bfb0c0121a1efcf9"}},{"code_sha256_prefix":"eb01e9140fccae39","entry":"LambdaThreshold","repo":"vibalcam/glofnd","repo_kind":"official","path":"bimodal/src/fast_clip/loss.py","file_url":"https://github.com/vibalcam/glofnd/blob/HEAD/bimodal/src/fast_clip/loss.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":"eb01e9140fccae39"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}