{"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/mitigating-noisy-correspondence-by","title":"Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning","arxiv_id":"2405.16996","date":"2024-05-27","proceeding":"CVPR 2024 1","authors":["Zihua Zhao","Mengxi Chen","Tianjie Dai","Jiangchao Yao","Bo Han","Ya zhang","Yanfeng Wang"],"abstract":"Noisy correspondence that refers to mismatches in cross-modal data pairs, is prevalent on human-annotated or web-crawled datasets. Prior approaches to leverage such data mainly consider the application of uni-modal noisy label learning without amending the impact on both cross-modal and intra-modal geometrical structures in multimodal learning. Actually, we find that both structures are effective to discriminate noisy correspondence through structural differences when being well-established. Inspired by this observation, we introduce a Geometrical Structure Consistency (GSC) method to infer the true correspondence. Specifically, GSC ensures the preservation of geometrical structures within and between modalities, allowing for the accurate discrimination of noisy samples based on structural differences. Utilizing these inferred true correspondence labels, GSC refines the learning of geometrical structures by filtering out the noisy samples. Experiments across four cross-modal datasets confirm that GSC effectively identifies noisy samples and significantly outperforms the current leading methods.","url_abs":"https://arxiv.org/abs/2405.16996v1","url_pdf":"https://arxiv.org/pdf/2405.16996v1.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":"mitigating-noisy-correspondence-by","repo_url":"https://github.com/MediaBrain-SJTU/GSC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-modal-retrieval-with-noisy","task_name":"Cross-modal retrieval with noisy correspondence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-1","task":"Cross-modal retrieval with noisy correspondence","dataset":"CC152K","model":"GSC-SGR","rank_in_archive_order":2,"of":15,"metrics":{"Image-to-text R@1":"42.1","Image-to-text R@10":"77.7","Image-to-text R@5":"68.4","R-Sum":"375.1","Text-to-image R@1":"42.2","Text-to-image R@10":"77.1","Text-to-image R@5":"67.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-3","task":"Cross-modal retrieval with noisy correspondence","dataset":"COCO-Noisy","model":"GSC-SGR","rank_in_archive_order":4,"of":17,"metrics":{"Image-to-text R@1":"79.5","Image-to-text R@10":"98.9","Image-to-text R@5":"96.4","R-Sum":"525.7","Text-to-image R@1":"64.4","Text-to-image R@10":"95.9","Text-to-image R@5":"90.6"},"uses_additional_data":false},{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-2","task":"Cross-modal retrieval with noisy correspondence","dataset":"Flickr30K-Noisy","model":"GSC-SGR","rank_in_archive_order":6,"of":16,"metrics":{"Image-to-text R@1":"78.3","Image-to-text R@10":"97.8","Image-to-text R@5":"94.6","R-Sum":"505.8","Text-to-image R@1":"60.1","Text-to-image R@10":"90.5","Text-to-image R@5":"84.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.16996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16996"}},"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/MediaBrain-SJTU/GSC","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"6367f1b6c81b200c","entry":"EncoderImage","repo":"MediaBrain-SJTU/GSC","repo_kind":"official","path":"GSC+/model/SGRAF.py","file_url":"https://github.com/MediaBrain-SJTU/GSC/blob/HEAD/GSC%2B/model/SGRAF.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":"6367f1b6c81b200c"}},{"code_sha256_prefix":"293f25516a30a67b","entry":"EncoderText","repo":"MediaBrain-SJTU/GSC","repo_kind":"official","path":"GSC+/model/SGRAF.py","file_url":"https://github.com/MediaBrain-SJTU/GSC/blob/HEAD/GSC%2B/model/SGRAF.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":"293f25516a30a67b"}},{"code_sha256_prefix":"349dcf4a43fd78cb","entry":"SCAN_attention","repo":"MediaBrain-SJTU/GSC","repo_kind":"official","path":"GSC+/model/SGRAF.py","file_url":"https://github.com/MediaBrain-SJTU/GSC/blob/HEAD/GSC%2B/model/SGRAF.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"349dcf4a43fd78cb"}},{"code_sha256_prefix":"e38cb6ed38f96a8f","entry":"VisualSA","repo":"MediaBrain-SJTU/GSC","repo_kind":"official","path":"GSC+/model/SGRAF.py","file_url":"https://github.com/MediaBrain-SJTU/GSC/blob/HEAD/GSC%2B/model/SGRAF.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e38cb6ed38f96a8f"}},{"code_sha256_prefix":"daf1dc307371b142","entry":"EncoderSimilarity","repo":"MediaBrain-SJTU/GSC","repo_kind":"official","path":"GSC+/model/SGRAF.py","file_url":"https://github.com/MediaBrain-SJTU/GSC/blob/HEAD/GSC%2B/model/SGRAF.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":"daf1dc307371b142"}},{"code_sha256_prefix":"a643c54061595d72","entry":"SGRAF","repo":"MediaBrain-SJTU/GSC","repo_kind":"official","path":"GSC+/model/SGRAF.py","file_url":"https://github.com/MediaBrain-SJTU/GSC/blob/HEAD/GSC%2B/model/SGRAF.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":"a643c54061595d72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}