Papers › ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for...

ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning

27 Feb 2025CVPR 2025 1arXiv:2502.19962archive 2025-07-28

Quanxing Zha, Xin Liu, Shu-Juan Peng, Yiu-ming Cheung, Xing Xu, Nannan Wang

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 5 code samples harvested from 1 repository linked to this paper: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qxzha/ReCon officialmentioned in paperpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran
2unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qxzha/ReCon. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

qxzha/ReCon official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
ContrastiveLoss in 16 papers models/SGRAF.py ran Apache-2.0 (permissive) · f6a9075db2f6b770 · report fixture: signature scores:Tensor/2/float, max_violation:bool/0/bool · returned Tensor · level recorded 2026-09-24
EncoderText in 8 papers models/SGRAF.py ran Apache-2.0 (permissive) · 9e9ce744fd9ea1bb · report fixture: returned EncoderText · level recorded 2026-09-22
SelfAttention in 66 papers models/SGRAF.py ran Apache-2.0 (permissive) · d4d6173d6e5117e7 · report fixture: signature all_embs:Tensor/2/float, n_img_regions:int/0/int, n_cap_words:int/0/int · returned tuple · level recorded 2026-09-24
EncoderSimilarity in 6 papers models/SGRAF.py unverified Apache-2.0 (permissive) · 272bb3135283e65e · report
SGRAF in 7 papers models/SGRAF.py unverified Apache-2.0 (permissive) · f7bb326e0936c7b4 · report

Tasks

Cross-Modal RetrievalCross-modal retrieval with noisy correspondenceImage-text RetrievalImage-text matching

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-modal retrieval with noisy correspondence CC152K ReCon Image-to-text R@1 43.1 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K ReCon Image-to-text R@10 78.1 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K ReCon Image-to-text R@5 68.7 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K ReCon R-Sum 380.5 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K ReCon Text-to-image R@1 44.9 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K ReCon Text-to-image R@10 77.4 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K ReCon Text-to-image R@5 68.3 #1 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon Image-to-text R@1 80.9 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon Image-to-text R@10 98.8 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon Image-to-text R@5 96.6 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon R-Sum 528.6 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon Text-to-image R@1 65.2 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon Text-to-image R@10 96.0 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy ReCon Text-to-image R@5 91.0 #1 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon Image-to-text R@1 80.3 #1 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon Image-to-text R@10 97.8 #1 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon Image-to-text R@5 95.3 #1 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon R-Sum 511.8 #1 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon Text-to-image R@1 61.6 #1 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon Text-to-image R@10 91.3 #1 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy ReCon Text-to-image R@5 85.5 #1 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections