Papers › Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

18 Apr 2018NeurIPS 2018 12arXiv:1804.06872archive 2025-07-28

Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama

Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of clean labels and then those of noisy labels. Therefore in this paper, we propose a new deep learning paradigm called Co-teaching for combating with noisy labels. Namely, we train two deep neural networks simultaneously, and let them teach each other given every mini-batch: firstly, each network feeds forward all data and selects some data of possibly clean labels; secondly, two networks communicate with each other what data in this mini-batch should be used for training; finally, each network back propagates the data selected by its peer network and updates itself. Empirical results on noisy versions of MNIST, CIFAR-10 and CIFAR-100 demonstrate that Co-teaching is much superior to the state-of-the-art methods in the robustness of trained deep models.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="1804.06872")

Code

Syntology Ran 7 of 7 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 3 ran · fixture could not drive it.

By repository: community (archive-listed): 7 samples from 2 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bhanML/Co-teaching officialmentioned in papermentioned on GitHubpytorch report
smilelab-fl/fednoisy mentioned on GitHubpytorch report
viethungluu/co-teaching mentioned on GitHubpytorch report
yeachan-kr/pytorch-coteaching mentioned on GitHubpytorch report
ziegler-ingo/cleavage_prediction mentioned on GitHubpytorch 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

7 samples harvested; 7 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
3ran · fixture could not drive it

Licence: 7 of the 7 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

call_bn yeachan-kr/pytorch-coteaching/models/modeling.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 7937f88152d63f61 · report
co_teaching_loss yeachan-kr/pytorch-coteaching/runs/train_coteaching.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 28ee0da938dd2072 · report
test_epoch viethungluu/co-teaching/trainer.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 8fe822efc60545de · report
test_step yeachan-kr/pytorch-coteaching/runs/train_coteaching.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 2cea1e0d0d4e2bef · report
train_coteaching viethungluu/co-teaching/trainer.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 18e4b217ddc27918 · report
train_epoch viethungluu/co-teaching/trainer.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · cb81e4c7990c2a14 · report
train_step yeachan-kr/pytorch-coteaching/runs/train_coteaching.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 5107b016c3d369b0 · report

Tasks

Image ClassificationLearning with noisy labelsMemorization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Clothing1M CoT Accuracy 70.15% #48 of 51 Archive leaderboard report
Image Classification mini WebVision 1.0 Co-teaching (Inception-ResNet-v2) ImageNet Top-1 Accuracy 61.48 #40 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 Co-teaching (Inception-ResNet-v2) ImageNet Top-5 Accuracy 84.70 #40 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 Co-teaching (Inception-ResNet-v2) Top-1 Accuracy 63.58 #40 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 Co-teaching (Inception-ResNet-v2) Top-5 Accuracy 85.20 #40 of 47 Archive leaderboard report
Learning with noisy labels CIFAR-100N Co-Teaching Accuracy (mean) 60.37 #10 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Aggregate Co-Teaching Accuracy (mean) 91.20 #18 of 26 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random1 Co-Teaching Accuracy (mean) 90.33 #11 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random2 Co-Teaching Accuracy (mean) 90.30 #11 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random3 Co-Teaching Accuracy (mean) 90.15 #9 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Worst Co-Teaching Accuracy (mean) 83.83 #11 of 25 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