Papers › Cross-modal Active Complementary Learning with Self-refining Correspondence

Cross-modal Active Complementary Learning with Self-refining Correspondence

26 Oct 2023NeurIPS 2023 11arXiv:2310.17468archive 2025-07-28

Yang Qin, Yuan Sun, Dezhong Peng, Joey Tianyi Zhou, Xi Peng, Peng Hu

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. However, most existing methods implicitly assume the training pairs are well-aligned while ignoring the ubiquitous annotation noise, a.k.a noisy correspondence (NC), thereby inevitably leading to a performance drop. Although some methods attempt to address such noise, they still face two challenging problems: excessive memorizing/overfitting and unreliable correction for NC, especially under high noise. To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods. Specifically, ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision, leading to theoretically and experimentally demonstrated robustness against NC. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences, thereby alleviating error accumulation and achieving accurate and stable corrections. We carry out extensive experiments on three image-text benchmarks, i.e., Flickr30K, MS-COCO, and CC152K, to verify the superior robustness of our CRCL against synthetic and real-world noisy correspondences.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 28 code samples: 27 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 28: 23 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 0 violated, 15 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 27 samples from 1 repository, 22 ran (17 with no instrument failure; 5 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

qinyang79/crcl officialmentioned in paperpytorchSyntology: 27 samples, 22 ran (5 instrument-failed) · 5 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

28 samples harvested: 23 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 0 violated, 15 with no contract checked; 6 where Syntology's instrument failed) · 5 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.

2ran · honoured contract
6ran · our draft was wrong
15ran
5unverified

Licence: 28 of the 28 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 qinyang79/crcl. 1 sample is listed last, in a group without a repository. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

qinyang79/crcl official repository 27 samples, 22 ran (5 instrument-failed) · 5 unverified
AttentionFiltration CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · 693b17df7b8c6055 · report fixture: returned AttentionFiltration · level recorded 2026-09-22
ContrastiveLoss in 16 papers CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0822e67441847823 · report fixture: returned ContrastiveLoss · level recorded 2026-09-22
EncoderImage in 9 papers CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4075e94c929dd49b · report fixture: returned EncoderImage · level recorded 2026-09-22
EncoderImageAggr CRCL_NeurIPS23/model/CRCL.py ran fingerprinted no licence file found · pointer only · 23bb367e48dddb94 · report fixture: signature images:Tensor/3/float, image_lengths:Tensor/1/float · returned Tensor · level recorded 2026-09-24
EncoderText in 8 papers CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · 87256eef10e84cf7 · report fixture: returned EncoderText · level recorded 2026-09-22
GPO CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · e8fda28aefdcfcdb · report fixture: returned GPO · level recorded 2026-09-22
MLP in 375 papers CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · 10426d360aea3d8e · report fixture: returned MLP · level recorded 2026-09-22
SCAN_attention CRCL_NeurIPS23/model/CRCL.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 74500030ae6c1b43 · report fixture: signature query:Tensor/3/float, context:Tensor/3/float, smooth:float/0/float · returned Tensor · level recorded 2026-09-22
TextSA CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · 83d9349f26c10e82 · report fixture: returned TextSA · level recorded 2026-09-22
VisualSA CRCL_NeurIPS23/model/CRCL.py ran · metamorphic tier: deterministic no licence file found · pointer only · c09ebb6e3e75d64c · report fixture: returned VisualSA · level recorded 2026-09-22
collate_fn in 500 papers CRCL_NeurIPS23/data.py ran no licence file found · pointer only · 498e6d8b90b78468 · report fixture: signature data:list/1/tuple · returned tuple · level recorded 2026-09-24
cosine_sim in 34 papers CRCL_NeurIPS23/model/SGRAF.py ran no licence file found · pointer only · 3a3ba65d84f3eeff · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-24
cosine_similarity_matrix in 8 papers CRCL_NeurIPS23/model/CRCL.py ran · honoured contract fingerprinted no licence file found · pointer only · 7b18bd64b585e4d2 · report fixture: signature a:ndarray/2/float, b:ndarray/2/float · returned ndarray · level recorded 2026-09-22
encode_data in 19 papers CRCL_NeurIPS23/evaluation.py ran no licence file found · pointer only · bdf65a1c26e5fec5 · report fixture: signature model:callable/0/?, data_loader:MockDataLoader/0/?, log_step:int/0/int, logging:callable/0/?, sub:int/0/int · returned tuple · level recorded 2026-09-24
from_txt in 5 papers CRCL_NeurIPS23/vocab.py ran no licence file found · pointer only · 414f20e131140e01 · report fixture: signature txt:str/0/str · returned list · level recorded 2026-09-24
get_precomp_loader in 5 papers CRCL_NeurIPS23/data.py ran no licence file found · pointer only · 091fa44320344aae · report fixture: signature data_path:str/0/str, data_split:str/0/str, vocab:callable/0/?, opt:Options/0/?, logger:Logger/0/? · returned DataLoader · level recorded 2026-09-24
l1norm in 14 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
CRCL_NeurIPS23/model/SGRAF.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b943467457f9825d · report fixture: signature X:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
l1norm in 14 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
CRCL_NeurIPS23/model/CRCL.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9bf455ab09372ab4 · report fixture: signature X:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
CRCL_NeurIPS23/model/VSEinfty.py ran · our draft was wrong fingerprinted no licence file found · pointer only · be7c4a676b9f1e19 · report fixture: signature X:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
CRCL_NeurIPS23/model/SGRAF.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 03e1f23d59a7c45a · report fixture: signature X:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
positional_encoding_1d CRCL_NeurIPS23/model/VSEinfty.py ran · honoured contract no licence file found · pointer only · 66c401f1c3fade5d · report fixture: signature d_model:int/0/int, length:int/0/int · returned Tensor · level recorded 2026-09-22
shard_attn_scores CRCL_NeurIPS23/evaluation.py ran no licence file found · pointer only · 7a82222075ccfaac · report fixture: signature model:callable/0/?, img_embs:ndarray/2/float, cap_embs:ndarray/2/float, cap_lens:list/1/int, opt:dict/0/?, shard_size:int/0/int · returned ndarray · level recorded 2026-09-24
CRCL CRCL_NeurIPS23/model/CRCL.py unverified no licence file found · pointer only · 52df4f2c82114f8a · report
EncoderSimilarity in 6 papers CRCL_NeurIPS23/model/CRCL.py unverified no licence file found · pointer only · 1cd408d8277e77a1 · report
SGRAF in 7 papers CRCL_NeurIPS23/model/CRCL.py unverified no licence file found · pointer only · d99c8e38277ee8a9 · report
VSEModel CRCL_NeurIPS23/model/CRCL.py unverified no licence file found · pointer only · 615b05a63a1c5cde · report
get_loaders in 51 papers CRCL_NeurIPS23/data.py unverified no licence file found · pointer only · c2c0455d61babb92 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_sim in 12 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 42cf9ff13b24ef29 · report fixture: signature images:Tensor/2/float, captions:Tensor/2/float · returned Tensor · level recorded 2026-09-22

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 Cross-modal Robust Complementary Learning framework (CRCL) (graph method: Cross-modal Robust Complementary Learning framework (CRCL)). 20 bricks; individually on a fixture: 16 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. CRCL entry · level 0 · unverified · 52df4f2c82114f8a
  2. SGRAF helper · level 0 · unverified · d99c8e38277ee8a9
  3. VSEModel helper · level 0 · unverified · 615b05a63a1c5cde
  4. cosine_similarity_matrix helper · level 1 · ran · honoured contract · 7b18bd64b585e4d2
  5. ContrastiveLoss loss · level 1 · ran · 0822e67441847823
  6. EncoderImage model · level 1 · ran · 4075e94c929dd49b
  7. EncoderSimilarity helper · level 0 · unverified · 1cd408d8277e77a1
  8. EncoderText model · level 1 · ran · 87256eef10e84cf7
  9. EncoderImageAggr helper · level 1 · ran · 23bb367e48dddb94
  10. get_sim helper · level 1 · ran · our draft was wrong · 42cf9ff13b24ef29
  11. l2norm helper · level 1 · ran · our draft was wrong · be7c4a676b9f1e19
  12. AttentionFiltration model · level 1 · ran · 693b17df7b8c6055
  13. GraphReasoning model · level 1 · ran · 42172bf6d3276ede
  14. SCAN_attention helper · level 1 · ran · our draft was wrong · 74500030ae6c1b43
  15. TextSA model · level 1 · ran · 83d9349f26c10e82
  16. VisualSA model · level 1 · ran · c09ebb6e3e75d64c
  17. GPO helper · level 1 · ran · e8fda28aefdcfcdb
  18. MLP helper · level 1 · ran · 10426d360aea3d8e
  19. l1norm helper · level 1 · ran · our draft was wrong · 9bf455ab09372ab4
  20. positional_encoding_1d helper · level 1 · ran · honoured contract · 66c401f1c3fade5d

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="2310.17468") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Cross-modal retrieval with noisy correspondenceImage-text matchingText Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-modal retrieval with noisy correspondence CC152K CRCL Image-to-text R@1 41.8 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K CRCL Image-to-text R@10 76.5 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K CRCL Image-to-text R@5 67.4 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K CRCL R-Sum 373.7 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K CRCL Text-to-image R@1 41.6 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K CRCL Text-to-image R@10 78.4 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence CC152K CRCL Text-to-image R@5 68.0 #4 of 15 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL Image-to-text R@1 79.6 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL Image-to-text R@10 98.7 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL Image-to-text R@5 96.1 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL R-Sum 525.6 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL Text-to-image R@1 64.7 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL Text-to-image R@10 95.9 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence COCO-Noisy CRCL Text-to-image R@5 90.6 #5 of 17 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL Image-to-text R@1 77.9 #4 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL Image-to-text R@10 98.3 #4 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL Image-to-text R@5 95.4 #4 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL R-Sum 507.8 #4 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL Text-to-image R@1 60.9 #4 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL Text-to-image R@10 90.6 #4 of 16 Archive leaderboard report
Cross-modal retrieval with noisy correspondence Flickr30K-Noisy CRCL Text-to-image R@5 84.7 #4 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