Papers › Noisy-Correspondence Learning for Text-to-Image Person Re-identification

Noisy-Correspondence Learning for Text-to-Image Person Re-identification

19 Aug 2023CVPR 2024 1arXiv:2308.09911archive 2025-07-28

Yang Qin, Yingke Chen, Dezhong Peng, Xi Peng, Joey Tianyi Zhou, Peng Hu

Text-to-image person re-identification (TIReID) is a compelling topic in the cross-modal community, which aims to retrieve the target person based on a textual query. Although numerous TIReID methods have been proposed and achieved promising performance, they implicitly assume the training image-text pairs are correctly aligned, which is not always the case in real-world scenarios. In practice, the image-text pairs inevitably exist under-correlated or even false-correlated, a.k.a noisy correspondence (NC), due to the low quality of the images and annotation errors. To address this problem, we propose a novel Robust Dual Embedding method (RDE) that can learn robust visual-semantic associations even with NC. Specifically, RDE consists of two main components: 1) A Confident Consensus Division (CCD) module that leverages the dual-grained decisions of dual embedding modules to obtain a consensus set of clean training data, which enables the model to learn correct and reliable visual-semantic associations. 2) A Triplet Alignment Loss (TAL) relaxes the conventional Triplet Ranking loss with the hardest negative samples to a log-exponential upper bound over all negative ones, thus preventing the model collapse under NC and can also focus on hard-negative samples for promising performance. We conduct extensive experiments on three public benchmarks, namely CUHK-PEDES, ICFG-PEDES, and RSTPReID, to evaluate the performance and robustness of our RDE. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on all three datasets. Code is available at https://github.com/QinYang79/RDE.

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 14 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 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: 14 samples from 1 repository, 12 ran (9 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.

QinYang79/RDE officialmentioned in paperpytorchSyntology: 14 samples, 12 ran (3 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

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
9ran
2unverified

Licence: 14 of the 14 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/RDE. “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. 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/RDE official repository 14 samples, 12 ran (3 instrument-failed) · 2 unverified
all_gather in 119 papers 2024-CVPR-RDE/datasets/sampler_ddp.py ran no licence file found · pointer only · 41f9842ca45bbf6f · report fixture: signature data:dict/0/?, group:NoneType/0/? · returned list · level recorded 2026-09-24
build_transforms in 10 papers 2024-CVPR-RDE/datasets/build.py ran no licence file found · pointer only · cb870e3cbf51d74a · report fixture: signature img_size:tuple/1/int, aug:bool/0/bool, is_train:bool/0/bool · returned Compose · level recorded 2026-09-24
collate in 50 papers 2024-CVPR-RDE/datasets/build.py ran · our draft was wrong no licence file found · pointer only · e1cb4f3d2779e452 · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-24
compute_InfoNCE_per 2024-CVPR-RDE/model/objectives.py ran no licence file found · pointer only · 6119e3ec8f8ddc67 · report fixture: signature scores:Tensor/2/float, logit_scale:Tensor/0/float · returned Tensor · level recorded 2026-09-24
compute_TRL_per 2024-CVPR-RDE/model/objectives.py ran no licence file found · pointer only · 40fec36e4f438546 · report fixture: signature scores:Tensor/2/float, pid:Tensor/1/int, margin:float/0/float, tau:float/0/float · returned Tensor · level recorded 2026-09-24
compute_sdm_per 2024-CVPR-RDE/model/objectives.py ran no licence file found · pointer only · 71daf1b42a4381cc · report fixture: signature scores:Tensor/2/float, pid:Tensor/1/float, logit_scale:Tensor/0/float, epsilon:float/0/float · returned Tensor · level recorded 2026-09-24
inject_noisy_correspondence 2024-CVPR-RDE/datasets/bases.py ran no licence file found · pointer only · e16c83f5e9bda25e · report fixture: signature dataset:list/1/tuple, noisy_rate:float/0/float, noisy_file:str/0/str · returned tuple · level recorded 2026-09-24
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
2024-CVPR-RDE/model/CrossEmbeddingLayer_tse.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
2024-CVPR-RDE/model/build.py ran fingerprinted no licence file found · pointer only · b39076605981f7f8 · report fixture: signature X:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-24
maxk_pool1d 2024-CVPR-RDE/model/CrossEmbeddingLayer_tse.py ran fingerprinted no licence file found · pointer only · 4e45e78d9ed12b30 · report fixture: signature x:Tensor/2/float, dim:int/0/int, k:int/0/int · returned Tensor · level recorded 2026-09-24
resize_pos_embed in 102 papers 2024-CVPR-RDE/model/clip_model.py ran · our draft was wrong no licence file found · pointer only · 489d084ef038d428 · report fixture: signature posemb:Tensor/2/float, posemb_new:Tensor/2/float, hight:int/0/int, width:int/0/int · returned Tensor · level recorded 2026-09-24
tokenize in 176 papers 2024-CVPR-RDE/datasets/bases.py ran no licence file found · pointer only · 3d862712396854e3 · report fixture: signature caption:str/0/str, tokenizer:MockTokenizer/0/?, text_length:int/0/int, truncate:bool/0/bool · returned Tensor · level recorded 2026-09-24
build_CLIP_from_openai_pretrained 2024-CVPR-RDE/model/clip_model.py unverified no licence file found · pointer only · 5defb038bfe378bb · report
maxk_pool1d_var 2024-CVPR-RDE/model/CrossEmbeddingLayer_tse.py unverified no licence file found · pointer only · 7c78dde9bea2b44d · report

Tasks

Person Re-IdentificationText based Person RetrievalText-based Person Retrieval with Noisy Correspondence

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text based Person Retrieval ICFG-PEDES RDE R@1 67.68 #3 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES RDE R@10 87.36 #3 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES RDE R@5 82.47 #3 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES RDE mAP 40.06 #3 of 12 Archive leaderboard report
Text based Person Retrieval ICFG-PEDES RDE mINP 7.87 #3 of 12 Archive leaderboard report
Text based Person Retrieval RSTPReid RDE R@1 65.35 #5 of 9 Archive leaderboard report
Text based Person Retrieval RSTPReid RDE R@10 89.90 #5 of 9 Archive leaderboard report
Text based Person Retrieval RSTPReid RDE R@5 83.95 #5 of 9 Archive leaderboard report
Text based Person Retrieval RSTPReid RDE mAP 50.88 #5 of 9 Archive leaderboard report
Text based Person Retrieval RSTPReid RDE mINP 28.08 #5 of 9 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES RDE Rank 10 93.63 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES RDE Rank-1 74.46 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES RDE Rank-5 89.42 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES RDE mAP 66.13 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence CUHK-PEDES RDE mINP 49.66 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES RDE Rank 1 66.54 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES RDE Rank-10 86.70 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES RDE Rank-5 81.70 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES RDE mAP 39.08 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence ICFG-PEDES RDE mINP 7.55 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid RDE Rank 1 64.45 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid RDE Rank 10 90.00 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid RDE Rank 5 83.50 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid RDE mAP 49.78 #1 of 6 Archive leaderboard report
Text-based Person Retrieval with Noisy Correspondence RSTPReid RDE mINP 27.43 #1 of 6 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.

Methods

Focus

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