{"url":"/task/cross-modal-retrieval-with-noisy","name":"Cross-modal retrieval with noisy correspondence","slug":"cross-modal-retrieval-with-noisy","description_markdown":"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.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":20,"papers_with_code":14,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-3","slug":"cross-modal-retrieval-with-noisy-3","dataset":"COCO-Noisy","dataset_url":"/dataset/coco-noisy","rows_in_archive":17,"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"],"first_row_in_archive_order":{"model":"ReCon","paper_title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","paper_url":"/paper/recon-enhancing-true-correspondence-1","paper_date":"2025-02-27","arxiv_id":"2502.19962","code_links":[{"title":"qxzha/ReCon","url":"https://github.com/qxzha/ReCon"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-2","slug":"cross-modal-retrieval-with-noisy-2","dataset":"Flickr30K-Noisy","dataset_url":"/dataset/flickr30k-20-nc-1k-test","rows_in_archive":16,"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"],"first_row_in_archive_order":{"model":"ReCon","paper_title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","paper_url":"/paper/recon-enhancing-true-correspondence-1","paper_date":"2025-02-27","arxiv_id":"2502.19962","code_links":[{"title":"qxzha/ReCon","url":"https://github.com/qxzha/ReCon"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/cross-modal-retrieval-with-noisy-1","slug":"cross-modal-retrieval-with-noisy-1","dataset":"CC152K","dataset_url":"/dataset/cc152k","rows_in_archive":15,"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"],"first_row_in_archive_order":{"model":"ReCon","paper_title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","paper_url":"/paper/recon-enhancing-true-correspondence-1","paper_date":"2025-02-27","arxiv_id":"2502.19962","code_links":[{"title":"qxzha/ReCon","url":"https://github.com/qxzha/ReCon"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cc152k","name":"CC152K","full_name":"Conceptual Captions 152K","num_papers_in_archive":17},{"url":"/dataset/coco-noisy","name":"COCO-Noisy","full_name":"Microsoft Common Objects in Context with 20% of Noisy Correspondence and 1K test data","num_papers_in_archive":17},{"url":"/dataset/flickr30k-20-nc-1k-test","name":"Flickr30K-Noisy","full_name":"Flickr-30K with 20% of Noisy Correspondence","num_papers_in_archive":16},{"url":"/dataset/now","name":"NoW","full_name":"Noise of Web","num_papers_in_archive":2},{"url":"/dataset/noise-of-web-now","name":"Noise of Web","full_name":"NoW","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":14,"of":14,"tagged_in_all":20,"items":[{"url":"/paper/negative-pre-aware-for-noisy-cross-modal","title":"Negative Pre-aware for Noisy Cross-modal Matching","date":"2023-12-10","arxiv_id":"2312.05777","repositories_listed":2,"syntology":null},{"url":"/paper/recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","arxiv_id":"2502.19962","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/pc-2-pseudo-classification-based-pseudo","title":"PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","date":"2024-08-02","arxiv_id":"2408.01349","repositories_listed":1,"syntology":null},{"url":"/paper/ugncl-uncertainty-guided-noisy-correspondence","title":"UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching","date":"2024-07-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-noisy-correspondence-by","title":"Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning","date":"2024-05-27","arxiv_id":"2405.16996","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/cross-modal-retrieval-with-noisy","title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","date":"2024-03-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-rematch-mismatched-pairs-for","title":"Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval","date":"2024-03-08","arxiv_id":"2403.05105","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":10}},{"url":"/paper/cross-modal-active-complementary-learning-1","title":"Cross-modal Active Complementary Learning with Self-refining Correspondence","date":"2023-10-26","arxiv_id":"2310.17468","repositories_listed":1,"syntology":{"n":28,"n_ran":23,"n_unverified":5,"n_pointer_only":28}},{"url":"/paper/noisy-correspondence-learning-with-meta","title":"Noisy Correspondence Learning with Meta Similarity Correction","date":"2023-04-13","arxiv_id":"2304.06275","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/integrating-language-guidance-into-image-text","title":"Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives","date":"2023-03-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bicro-noisy-correspondence-rectification-for","title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","date":"2023-03-22","arxiv_id":"2303.12419","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":11}},{"url":"/paper/cross-modal-retrieval-with-partially","title":"Cross-Modal Retrieval with Partially Mismatched Pairs","date":"2023-02-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-evidential-learning-with-noisy","title":"Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval","date":"2022-10-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-noisy-correspondence-for-cross","title":"Learning with Noisy Correspondence for Cross-modal Matching","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}