Papers › BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional...
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
Shuo Yang, Zhaopan Xu, Kai Wang, Yang You, Hongxun Yao, Tongliang Liu, Min Xu
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, massive and correctly aligned data pairs are required for model training. However, unlike unimodal datasets, multimodal datasets are extremely harder to collect and annotate precisely. As an alternative, the co-occurred data pairs (e.g., image-text pairs) collected from the Internet have been widely exploited in the area. Unfortunately, the cheaply collected dataset unavoidably contains many mismatched data pairs, which have been proven to be harmful to the model's performance. To address this, we propose a general framework called BiCro (Bidirectional Cross-modal similarity consistency), which can be easily integrated into existing cross-modal matching models and improve their robustness against noisy data. Specifically, BiCro aims to estimate soft labels for noisy data pairs to reflect their true correspondence degree. The basic idea of BiCro is motivated by that -- taking image-text matching as an example -- similar images should have similar textual descriptions and vice versa. Then the consistency of these two similarities can be recast as the estimated soft labels to train the matching model. The experiments on three popular cross-modal matching datasets demonstrate that our method significantly improves the noise-robustness of various matching models, and surpass the state-of-the-art by a clear margin.
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):
get_harvested_code_for_paper(arxiv_id="2303.12419")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2303.12419", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2303.12419")
Code
Syntology 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 11 samples from 1 repository, 9 ran (6 with no instrument failure; 3 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.
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
11 samples harvested: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 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.
Licence: 11 of the 11 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 xu5zhao/bicro. “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.
0cd009249fea46c5 · report
fixture: returned AttentionFiltration · level recorded 2026-09-22 8195ef599b6ffb8c · report
fixture: signature scores:Tensor/2/float, hard_negative:bool/0/bool, labels:Tensor/1/float, soft_margin:str/0/str, mode:str/0/str, noise_tem:float/0/float · returned Tensor · level recorded 2026-09-24 bf08ee741b5ed5fb · report
fixture: returned EncoderImage · level recorded 2026-09-22 4d9bde26decdd78e · report
fixture: signature b:Tensor/2/float, a:Tensor/2/float · returned Tensor · level recorded 2026-09-22 a3a3d96d877b86ac · report
fixture: returned GraphReasoning · level recorded 2026-09-22 65f3e1e2d6b67aff · report
fixture: signature clean_input:Tensor/2/float, noise_input:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 e448a20d40c5d40b · report
fixture: signature index:Tensor/2/float, value:Tensor/2/float · returned Tensor · level recorded 2026-09-22 b80dc7ccec06c165 · report
fixture: returned TextSA · level recorded 2026-09-22 75ca7806acfbf329 · report
fixture: returned VisualSA · level recorded 2026-09-22 6939b038c1eaf5b5 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for BiCro (graph method: BiCro). 15 bricks; individually on a fixture: 13 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
- SGRAF entry · level 0 · unverified ·
26998b9b97c6ed92 - ContrastiveLoss loss · level 1 · ran ·
8195ef599b6ffb8c - EncoderImage model · level 1 · ran ·
bf08ee741b5ed5fb - EncoderSimilarity model · level 0 · unverified ·
6939b038c1eaf5b5 - EncoderText model · level 1 · ran ·
9e9ce744fd9ea1bb - EuclideanDistances helper · level 1 · ran · our draft was wrong ·
4d9bde26decdd78e - SIM_PAIR helper · level 1 · ran · our draft was wrong ·
65f3e1e2d6b67aff - SIM_SELE helper · level 1 · ran · our draft was wrong ·
e448a20d40c5d40b - l2norm helper · level 1 · ran · our draft was wrong ·
03e1f23d59a7c45a - AttentionFiltration model · level 1 · ran ·
0cd009249fea46c5 - GraphReasoning model · level 1 · ran ·
a3a3d96d877b86ac - SCAN_attention helper · level 1 · ran; the contract check could not run ·
7ec3bfb5f7f9023e - TextSA model · level 1 · ran ·
b80dc7ccec06c165 - VisualSA model · level 1 · ran ·
75ca7806acfbf329 - l1norm helper · level 1 · ran · our draft was wrong ·
b943467457f9825d
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.12419") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
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