SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.17468 · NeurIPS · 2023

Cross-modal Active Complementary Learning with Self-refining Correspondence

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

arXiv · PDF · Open in the Atlas

Code that ran

23 of 28 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 12 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2310.17468.json · badge: /api/ran/2310.17468.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
qinyang79/crcl canonical (classifier label)
classifier basis: classifier_2025
12 ran · 4 no recorded run
QinYang79/CRCL canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
AttentionFiltration Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("693b17df7b8c6055")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ContrastiveLoss Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("0822e67441847823")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EncoderImage Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("4075e94c929dd49b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EncoderImageAggr Ran
ran on a synthesized input
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("23bb367e48dddb94")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EncoderText Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("87256eef10e84cf7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GPO Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("e8fda28aefdcfcdb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

MLP Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("10426d360aea3d8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SCAN_attention Ran
ran; our contract draft was wrong, not the code
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("74500030ae6c1b43")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TextSA Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("83d9349f26c10e82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

VisualSA Ran
ran on a synthesized input · constructed an object; no result was computed
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("c09ebb6e3e75d64c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

collate_fn Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/data.py
pointer only (licence: NONE) · get_code("498e6d8b90b78468")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cosine_sim Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/model/SGRAF.py
pointer only (licence: NONE) · get_code("3a3ba65d84f3eeff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cosine_similarity_matrix Ran
ran, honoured the contract we drafted
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("7b18bd64b585e4d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

encode_data Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/evaluation.py
pointer only (licence: NONE) · get_code("bdf65a1c26e5fec5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

from_txt Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/vocab.py
pointer only (licence: NONE) · get_code("414f20e131140e01")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_precomp_loader Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/data.py
pointer only (licence: NONE) · get_code("091fa44320344aae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_sim Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from gair-lab/iisan
pointer only; the stored copy get_code serves, from gair-lab/iisan, is pointer only (licence: NONE) · get_code("42cf9ff13b24ef29")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l1norm Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/model/SGRAF.py
pointer only (licence: NONE); the stored copy get_code serves, from Paranioar/SGRAF, is pointer only (licence: NONE) · get_code("b943467457f9825d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l1norm Ran
ran; our contract draft was wrong, not the code
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("9bf455ab09372ab4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l2norm Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/model/VSEinfty.py
pointer only (licence: NONE) · get_code("be7c4a676b9f1e19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l2norm Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/model/SGRAF.py
pointer only (licence: NONE); the stored copy get_code serves, from Paranioar/SGRAF, is pointer only (licence: NONE) · get_code("03e1f23d59a7c45a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

positional_encoding_1d Ran
ran, honoured the contract we drafted
QinYang79/CRCL/CRCL_NeurIPS23/model/VSEinfty.py
pointer only (licence: NONE); the stored copy get_code serves, from woodfrog/poly-diffuse, is pointer only (licence: GPL-3.0) · get_code("66c401f1c3fade5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

shard_attn_scores Ran
ran; our contract draft was wrong, not the code
QinYang79/CRCL/CRCL_NeurIPS23/evaluation.py
pointer only (licence: NONE) · get_code("7a82222075ccfaac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CRCL Not yet run
unverified (harvested, no recorded run)
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("52df4f2c82114f8a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

EncoderSimilarity Not yet run
unverified (harvested, no recorded run)
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("1cd408d8277e77a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

SGRAF Not yet run
unverified (harvested, no recorded run)
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("d99c8e38277ee8a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

VSEModel Not yet run
unverified (harvested, no recorded run)
qinyang79/crcl/CRCL_NeurIPS23/model/CRCL.py
pointer only (licence: NONE) · get_code("615b05a63a1c5cde")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qinyang79/crcl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_loaders Not yet run
unverified (harvested, no recorded run)
QinYang79/CRCL/CRCL_NeurIPS23/data.py
pointer only (licence: NONE) · get_code("c2c0455d61babb92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, QinYang79/CRCL when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 28 samples lifted from this paper's linked repositories, 28 carry a function identity and 0 do not. Of the 27 distinct functions with an identity, 14 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 2 the same month, 11 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
l1norm
brick of this paper's assembly: helper
12 other papers
5 dated earlier, 1 the same month, 6 later · 3 only as an assembly brick
1803.08024 (2018-03)
Stacked Cross Attention for Image-Text Matching
2010.03403 (2020-10)
Universal Weighting Metric Learning for Cross-Modal Matching
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
and 9 more not named here
l2norm
brick of this paper's assembly: helper
12 other papers
8 dated earlier, 1 the same month, 3 later · 2 only as an assembly brick
1803.08024 (2018-03)
Stacked Cross Attention for Image-Text Matching
1904.01310 (2019-04)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
2010.03403 (2020-10)
Universal Weighting Metric Learning for Cross-Modal Matching
and 9 more not named here
l2norm 7 other papers
5 dated earlier, 2 later · 4 only as an assembly brick
1909.05506 (2019-09)
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
2303.11755 (2023-03)
LIMITR: Leveraging Local Information for Medical Image-Text Representation
and 4 more not named here
AttentionFiltration
brick of this paper's assembly: model
4 other papers
2 dated earlier, 2 later · 2 only as an assembly brick
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
2303.12419 (2023-03)
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
2403.05105 (2024-03)
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
and 1 more not named here
TextSA
brick of this paper's assembly: model
4 other papers
2 dated earlier, 2 later · 2 only as an assembly brick
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
2303.12419 (2023-03)
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
2403.05105 (2024-03)
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
and 1 more not named here
EncoderImage
brick of this paper's assembly: model
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
2303.12419 (2023-03)
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
2403.05105 (2024-03)
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
SCAN_attention
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 2 only as an assembly brick
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
2303.12419 (2023-03)
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
2403.05105 (2024-03)
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
VisualSA
brick of this paper's assembly: model
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
2303.12419 (2023-03)
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
2403.05105 (2024-03)
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval
positional_encoding_1d
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
2103.11161 (2021-03)
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
2305.18171 (2023-05)
Improved Probabilistic Image-Text Representations
2025.acl-long.61 (2025 (year only))
Modeling Uncertainty in Composed Image Retrieval via Probabilistic Embeddings
EncoderSimilarity
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2101.01368 (2021-01)
Similarity Reasoning and Filtration for Image-Text Matching
GPO
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2305.18171 (2023-05)
Improved Probabilistic Image-Text Representations
MLP
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2305.18171 (2023-05)
Improved Probabilistic Image-Text Representations
SGRAF
brick of this paper's assembly: helper
1 other paper
1 later
2502.19962 (2025-02)
ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning
get_sim
brick of this paper's assembly: helper
1 other paper
1 later
2404.02059 (2024-04)
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. Code is available at https://github.com/QinYang79/CRCL.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.17468")
get_code_for_paper("2310.17468")
have("2310.17468")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.17468.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.17468.svg)](https://syntology.ai/paper/2310.17468)

Connect an agent — have() is free.