{"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/recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","arxiv_id":"2502.19962","date":"2025-02-27","proceeding":"CVPR 2025 1","authors":["Quanxing Zha","Xin Liu","Shu-Juan Peng","Yiu-ming Cheung","Xing Xu","Nannan Wang"],"abstract":"Can we accurately identify the true correspondences from multimodal datasets containing mismatched data pairs? Existing methods primarily emphasize the similarity matching between the representations of objects across modalities, potentially neglecting the crucial relation consistency within modalities that are particularly important for distinguishing the true and false correspondences. Such an omission often runs the risk of misidentifying negatives as positives, thus leading to unanticipated performance degradation. To address this problem, we propose a general Relation Consistency learning framework, namely ReCon, to accurately discriminate the true correspondences among the multimodal data and thus effectively mitigate the adverse impact caused by mismatches. Specifically, ReCon leverages a novel relation consistency learning to ensure the dual-alignment, respectively of, the cross-modal relation consistency between different modalities and the intra-modal relation consistency within modalities. Thanks to such dual constrains on relations, ReCon significantly enhances its effectiveness for true correspondence discrimination and therefore reliably filters out the mismatched pairs to mitigate the risks of wrong supervisions. Extensive experiments on three widely-used benchmark datasets, including Flickr30K, MS-COCO, and Conceptual Captions, are conducted to demonstrate the effectiveness and superiority of ReCon compared with other SOTAs. The code is available at: https://github.com/qxzha/ReCon.","url_abs":"https://arxiv.org/abs/2502.19962v2","url_pdf":"https://arxiv.org/pdf/2502.19962v2.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":"recon-enhancing-true-correspondence-1","repo_url":"https://github.com/qxzha/ReCon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"cross-modal-retrieval-with-noisy","task_name":"Cross-modal retrieval with noisy correspondence"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-1","task":"Cross-modal retrieval with noisy correspondence","dataset":"CC152K","model":"ReCon","rank_in_archive_order":1,"of":15,"metrics":{"Image-to-text R@1":"43.1","Image-to-text R@10":"78.1","Image-to-text R@5":"68.7","R-Sum":"380.5","Text-to-image R@1":"44.9","Text-to-image R@10":"77.4","Text-to-image R@5":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-3","task":"Cross-modal retrieval with noisy correspondence","dataset":"COCO-Noisy","model":"ReCon","rank_in_archive_order":1,"of":17,"metrics":{"Image-to-text R@1":"80.9","Image-to-text R@10":"98.8","Image-to-text R@5":"96.6","R-Sum":"528.6","Text-to-image R@1":"65.2","Text-to-image R@10":"96.0","Text-to-image R@5":"91.0"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-2","task":"Cross-modal retrieval with noisy correspondence","dataset":"Flickr30K-Noisy","model":"ReCon","rank_in_archive_order":1,"of":16,"metrics":{"Image-to-text R@1":"80.3","Image-to-text R@10":"97.8","Image-to-text R@5":"95.3","R-Sum":"511.8","Text-to-image R@1":"61.6","Text-to-image R@10":"91.3","Text-to-image R@5":"85.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19962"}},"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/qxzha/ReCon","reach":null}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"f6a9075db2f6b770","entry":"ContrastiveLoss","repo":"qxzha/ReCon","repo_kind":"official","path":"models/SGRAF.py","file_url":"https://github.com/qxzha/ReCon/blob/HEAD/models/SGRAF.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6a9075db2f6b770"}},{"code_sha256_prefix":"9e9ce744fd9ea1bb","entry":"EncoderText","repo":"qxzha/ReCon","repo_kind":"official","path":"models/SGRAF.py","file_url":"https://github.com/qxzha/ReCon/blob/HEAD/models/SGRAF.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9e9ce744fd9ea1bb"}},{"code_sha256_prefix":"d4d6173d6e5117e7","entry":"SelfAttention","repo":"qxzha/ReCon","repo_kind":"official","path":"models/SGRAF.py","file_url":"https://github.com/qxzha/ReCon/blob/HEAD/models/SGRAF.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4d6173d6e5117e7"}},{"code_sha256_prefix":"272bb3135283e65e","entry":"EncoderSimilarity","repo":"qxzha/ReCon","repo_kind":"official","path":"models/SGRAF.py","file_url":"https://github.com/qxzha/ReCon/blob/HEAD/models/SGRAF.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":"272bb3135283e65e"}},{"code_sha256_prefix":"f7bb326e0936c7b4","entry":"SGRAF","repo":"qxzha/ReCon","repo_kind":"official","path":"models/SGRAF.py","file_url":"https://github.com/qxzha/ReCon/blob/HEAD/models/SGRAF.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":"f7bb326e0936c7b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}