Papers › Learning with Neighbor Consistency for Noisy Labels

Learning with Neighbor Consistency for Noisy Labels

4 Feb 2022CVPR 2022 1arXiv:2202.02200archive 2025-07-28

Ahmet Iscen, Jack Valmadre, Anurag Arnab, Cordelia Schmid

Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning from noisy labels that leverages similarities between training examples in feature space, encouraging the prediction of each example to be similar to its nearest neighbours. Compared to training algorithms that use multiple models or distinct stages, our approach takes the form of a simple, additional regularization term. It can be interpreted as an inductive version of the classical, transductive label propagation algorithm. We thoroughly evaluate our method on datasets evaluating both synthetic (CIFAR-10, CIFAR-100) and realistic (mini-WebVision, WebVision, Clothing1M, mini-ImageNet-Red) noise, and achieve competitive or state-of-the-art accuracies across all of them.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2202.02200")

Code

Syntology Ran 4 of 4 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 4 ran · fixture could not drive it.

By repository: official repository: 4 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google-research/scenic officialmentioned in papermentioned on GitHubjax 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

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

4ran · fixture could not drive it

Licence: 0 of the 4 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 google-research/scenic. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

get_knn google-research/scenic/scenic/projects/ncr/loss.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 06fab7164d5f04d0 · report
l2_normalize google-research/scenic/scenic/projects/ncr/loss.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · d473d69bb4e6da8e · report
ncr_loss google-research/scenic/scenic/projects/ncr/loss.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · f1339fb095cb07a5 · report
pairwise_kl_loss google-research/scenic/scenic/projects/ncr/loss.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 78743aa08f1f1c21 · report

Tasks

Image ClassificationLearning with noisy labels

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Red MiniImageNet 20% label noise NCR (ResNet-18) Accuracy 69.0 #1 of 5 Archive leaderboard report
Image Classification Red MiniImageNet 40% label noise NCR (ResNet-18) Accuracy 64.6 #1 of 5 Archive leaderboard report
Image Classification Red MiniImageNet 80% label noise NCR (ResNet-18) Accuracy 51.2 #1 of 5 Archive leaderboard report
Image Classification WebVision-1000 NCR+Mixup+DA (ResNet-50) Top-1 Accuracy 76.8 #4 of 16 Archive leaderboard report
Image Classification WebVision-1000 NCR (ResNet-50) Top-1 Accuracy 75.7% #8 of 16 Archive leaderboard report
Image Classification mini WebVision 1.0 NCR+Mixup+DA (ResNet-50) Top-1 Accuracy 80.5 #7 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 NCR+Mixup (ResNet-50) Top-1 Accuracy 79.4 #16 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 NCR (ResNet-50) Top-1 Accuracy 77.1 #32 of 47 Archive leaderboard report
Learning with noisy labels Red MiniImageNet 20% label noise NCR (ResNet-18) Test Accuracy 69.0 #1 of 4 Archive leaderboard report
Learning with noisy labels Red MiniImageNet 40% label noise NCR (ResNet-18) Test Accuracy 64.6 #1 of 4 Archive leaderboard report
Learning with noisy labels Red MiniImageNet 80% label noise NCR (ResNet-18) Test Accuracy 51.2 #1 of 4 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