Cross-modal retrieval with noisy correspondence

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

14 shown of 14 papers with code (20 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Negative Pre-aware for Noisy Cross-modal Matching
  10 Dec 2023 2 repositories listed
  Since clean samples are easier distinguished by GMM with increasing noise, the memory bank can still maintain high quality at a high noise ratio.
• ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning
  27 Feb 2025 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  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…
• PC²: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
  2 Aug 2024 1 repository listed
  In the realm of cross-modal retrieval, seamlessly integrating diverse modalities within multimedia remains a formidable challenge, especially given the complexities introduced by noisy correspondence learning (NCL).
• UGNCL: Uncertainty-Guided Noisy Correspondence Learning for Efficient Cross-Modal Matching
  11 Jul 2024 1 repository listed
  Cross-modal matching has recently gained significant popularity to facilitate retrieval across multi-modal data, and existing works are highly relied on an implicit assumption that the training data pairs are perfectly…
• Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
  27 May 2024 1 repository listed Syntology ran 4 of 6 samples · 2 unverified · 6 pointer-only (licence)
  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.
• Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining
  25 Mar 2024 1 repository listed
  Thanks to the consistency refining and mining strategy of CREAM, the overfitting on the false positives could be prevented and the consistency rooted in the false negatives could be exploited, thus leading to a robust…
• Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
  8 Mar 2024 1 repository listed Syntology ran 8 of 10 samples · 2 unverified · 10 pointer-only (licence)
  To achieve this, we propose L2RM, a general framework based on Optimal Transport (OT) that learns to rematch mismatched pairs.
• Cross-modal Active Complementary Learning with Self-refining Correspondence
  26 Oct 2023 1 repository listed Syntology ran 23 of 28 samples · 5 unverified · 28 pointer-only (licence)
  Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities.
• Noisy Correspondence Learning with Meta Similarity Correction
  13 Apr 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data.
• Integrating Language Guidance Into Image-Text Matching for Correcting False Negatives
  24 Mar 2023 1 repository listed
  Extensive experiments on two ITM benchmarks show that our method can improve the performance of existing ITM models.
• BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
  22 Mar 2023 1 repository listed Syntology ran 9 of 11 samples · 2 unverified · 11 pointer-only (licence)
  As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space.
• Cross-Modal Retrieval with Partially Mismatched Pairs
  22 Feb 2023 1 repository listed
  On the one hand, our method only utilizes the negative information which is much less likely false compared with the positive information, thus avoiding the overfitting issue to PMPs.
• Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval
  10 Oct 2022 1 repository listed
  However, it will unavoidably introduce noise (i.
• Learning with Noisy Correspondence for Cross-modal Matching
  1 Dec 2021 1 repository listed
  Based on this observation, we reveal and study a latent and challenging direction in cross-modal matching, named noisy correspondence, which could be regarded as a new paradigm of noisy labels.

Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.