{"url":"/sota/cross-modal-retrieval-with-noisy-2","task":{"name":"Cross-modal retrieval with noisy correspondence","url":"/task/cross-modal-retrieval-with-noisy","note":null},"dataset":{"name":"Flickr30K-Noisy","url":"/dataset/flickr30k-20-nc-1k-test"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"Noisy correspondence learning aims to eliminate the negative impact of the mismatched pairs (e.g., false positives/negatives) instead of annotation errors in several tasks.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["R-Sum","Image-to-text R@1","Image-to-text R@5","Image-to-text R@10","Text-to-image R@1","Text-to-image R@5","Text-to-image R@10"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"R-Sum":null,"Image-to-text R@1":null,"Image-to-text R@5":null,"Image-to-text R@10":null,"Text-to-image R@1":null,"Text-to-image R@5":null,"Text-to-image R@10":null}},"counts":{"rows":16,"rows_with_code":11,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ReCon","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,"paper_date":"2025-02-27","paper":"/paper/recon-enhancing-true-correspondence-1","paper_url":"https://arxiv.org/abs/2502.19962v2","paper_title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","code":"https://github.com/qxzha/ReCon","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CTPR-SGR","metrics":{"Image-to-text R@1":"76.2","Image-to-text R@10":"98.3","Image-to-text R@5":"95.8","R-Sum":"508.7","Text-to-image R@1":"60.5","Text-to-image R@10":"92.7","Text-to-image R@5":"85.2"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/learning-from-noisy-correspondence-with-tri","paper_url":"https://ieeexplore.ieee.org/document/10258402","paper_title":"Learning From Noisy Correspondence With Tri-Partition for Cross-Modal Matching","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SREM","metrics":{"Image-to-text R@1":"79.5","Image-to-text R@10":"97.9","Image-to-text R@5":"94.2","R-Sum":"507.8","Text-to-image R@1":"61.2","Text-to-image R@10":"90.2","Text-to-image R@5":"84.8"},"uses_additional_data":false,"paper_date":"2023-12-27","paper":"/paper/noisy-correspondence-learning-with-self","paper_url":"https://arxiv.org/abs/2312.16478v1","paper_title":"Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"CRCL","metrics":{"Image-to-text R@1":"77.9","Image-to-text R@10":"98.3","Image-to-text R@5":"95.4","R-Sum":"507.8","Text-to-image R@1":"60.9","Text-to-image R@10":"90.6","Text-to-image R@5":"84.7"},"uses_additional_data":false,"paper_date":"2023-10-26","paper":"/paper/cross-modal-active-complementary-learning-1","paper_url":"https://arxiv.org/abs/2310.17468v2","paper_title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","code":"https://github.com/qinyang79/crcl","n_code_links":1,"syntology":{"n_ran":23,"n_unverified":5,"n_samples":28,"n_pointer_only_licence":28}},{"rank_in_archive_order":5,"model":"NAC","metrics":{"Image-to-text R@1":"79.3","Image-to-text R@10":"97.8","Image-to-text R@5":"94.6","R-Sum":"507.1","Text-to-image R@1":"60.8","Text-to-image R@10":"90.1","Text-to-image R@5":"84.5"},"uses_additional_data":false,"paper_date":"2024-03-18","paper":"/paper/nac-mitigating-noisy-correspondence-in-cross","paper_url":"https://ieeexplore.ieee.org/document/10448059","paper_title":"NAC: Mitigating Noisy Correspondence in Cross-Modal Matching Via Neighbor Auxiliary Corrector","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"GSC-SGR","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,"paper_date":"2024-05-27","paper":"/paper/mitigating-noisy-correspondence-by","paper_url":"https://arxiv.org/abs/2405.16996v1","paper_title":"Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning","code":"https://github.com/MediaBrain-SJTU/GSC","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":7,"model":"UGNCL","metrics":{"Image-to-text R@1":"78.4","Image-to-text R@10":"97.8","Image-to-text R@5":"95.8","R-Sum":"505.6","Text-to-image R@1":"59.8","Text-to-image R@10":"89.5","Text-to-image R@5":"84.3"},"uses_additional_data":false,"paper_date":"2024-07-11","paper":"/paper/ugncl-uncertainty-guided-noisy-correspondence","paper_url":"https://dl.acm.org/doi/10.1145/3626772.3657806","paper_title":"UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching","code":"https://github.com/qxzha/UGNCL","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"BiCro*","metrics":{"Image-to-text R@1":"78.1","Image-to-text R@10":"97.5","Image-to-text R@5":"94.4","R-Sum":"504.7","Text-to-image R@1":"60.4","Text-to-image R@10":"89.9","Text-to-image R@5":"84.4"},"uses_additional_data":false,"paper_date":"2023-03-22","paper":"/paper/bicro-noisy-correspondence-rectification-for","paper_url":"https://arxiv.org/abs/2303.12419v2","paper_title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","code":"https://github.com/xu5zhao/bicro","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":9,"model":"REPAIR","metrics":{"Image-to-text R@1":"79.2","Image-to-text R@10":"96.9","Image-to-text R@5":"95.0","R-Sum":"504.4","Text-to-image R@1":"59.4","Text-to-image R@10":"89.5","Text-to-image R@5":"84.4"},"uses_additional_data":false,"paper_date":"2024-03-13","paper":"/paper/repair-rank-correlation-and-noisy-pair-half","paper_url":"https://arxiv.org/abs/2403.08224v1","paper_title":"REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"L2RM-SGRAF","metrics":{"Image-to-text R@1":"77.9","Image-to-text R@10":"97.8","Image-to-text R@5":"95.2","R-Sum":"503.8","Text-to-image R@1":"59.8","Text-to-image R@10":"89.5","Text-to-image R@5":"83.6"},"uses_additional_data":false,"paper_date":"2024-03-08","paper":"/paper/learning-to-rematch-mismatched-pairs-for","paper_url":"https://arxiv.org/abs/2403.05105v1","paper_title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","code":"https://github.com/hhc1997/l2rm","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":11,"model":"CREAM","metrics":{"Image-to-text R@1":"77.4","Image-to-text R@10":"97.3","Image-to-text R@5":"95.0","R-Sum":"502.3","Text-to-image R@1":"58.7","Text-to-image R@10":"89.8","Text-to-image R@5":"84.1"},"uses_additional_data":false,"paper_date":"2024-03-25","paper":"/paper/cross-modal-retrieval-with-noisy","paper_url":"https://ieeexplore.ieee.org/document/10477322","paper_title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","code":"https://github.com/XLearning-SCU/2024-TIP-CREAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"MSCN","metrics":{"Image-to-text R@1":"77.4","Image-to-text R@10":"97.6","Image-to-text R@5":"94.9","R-Sum":"501.9","Text-to-image R@1":"59.6","Text-to-image R@10":"89.2","Text-to-image R@5":"83.2"},"uses_additional_data":false,"paper_date":"2023-04-13","paper":"/paper/noisy-correspondence-learning-with-meta","paper_url":"https://arxiv.org/abs/2304.06275v1","paper_title":"Noisy Correspondence Learning with Meta Similarity Correction","code":"https://github.com/hhc1997/mscn","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"LNC","metrics":{"Image-to-text R@1":"76.3","Image-to-text R@10":"96.9","Image-to-text R@5":"93.7","R-Sum":"498.9","Text-to-image R@1":"58.4","Text-to-image R@10":"89.8","Text-to-image R@5":"83.8"},"uses_additional_data":false,"paper_date":"2024-04-13","paper":"/paper/learning-with-noisy-correspondence","paper_url":"https://link.springer.com/article/10.1007/s11263-024-02064-0","paper_title":"Learning with Noisy Correspondence","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"NCR","metrics":{"Image-to-text R@1":"75.0","Image-to-text R@10":"97.5","Image-to-text R@5":"93.9","R-Sum":"496.7","Text-to-image R@1":"58.3","Text-to-image R@10":"89.0","Text-to-image R@5":"83.0"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/learning-with-noisy-correspondence-for-cross","paper_url":"http://proceedings.neurips.cc/paper/2021/hash/f5e62af885293cf4d511ceef31e61c80-Abstract.html","paper_title":"Learning with Noisy Correspondence for Cross-modal Matching","code":"https://github.com/XLearning-SCU/2021-NeurIPS-NCR","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"DECL-SGRAF","metrics":{"Image-to-text R@1":"77.5","Image-to-text R@10":"97.0","Image-to-text R@5":"93.8","R-Sum":"494.7","Text-to-image R@1":"56.1","Text-to-image R@10":"88.5","Text-to-image R@5":"81.8"},"uses_additional_data":false,"paper_date":"2022-10-10","paper":"/paper/deep-evidential-learning-with-noisy","paper_url":"https://dl.acm.org/doi/abs/10.1145/3503161.3547922","paper_title":"Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval","code":"https://github.com/qinyang79/decl","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"RCL-SGR","metrics":{"Image-to-text R@1":"74.2","Image-to-text R@10":"96.9","Image-to-text R@5":"91.8","R-Sum":"487.2","Text-to-image R@1":"55.6","Text-to-image R@10":"87.5","Text-to-image R@5":"81.2"},"uses_additional_data":false,"paper_date":"2023-02-22","paper":"/paper/cross-modal-retrieval-with-partially","paper_url":"https://ieeexplore.ieee.org/document/10050111","paper_title":"Cross-Modal Retrieval with Partially Mismatched Pairs","code":"https://github.com/penghu-cs/RCL","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":49,"n_unverified":13,"n_samples":62,"n_pointer_only_licence":55,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":49,"n_unverified":13,"n_samples":62,"n_pointer_only_licence":55,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}