Papers › DivideMix: Learning with Noisy Labels as Semi-supervised Learning

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

18 Feb 2020ICLR 2020 1arXiv:2002.07394archive 2025-07-28

Junnan Li, Richard Socher, Steven C. H. Hoi

Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set with noisy samples, and trains the model on both the labeled and unlabeled data in a semi-supervised manner. To avoid confirmation bias, we simultaneously train two diverged networks where each network uses the dataset division from the other network. During the semi-supervised training phase, we improve the MixMatch strategy by performing label co-refinement and label co-guessing on labeled and unlabeled samples, respectively. Experiments on multiple benchmark datasets demonstrate substantial improvements over state-of-the-art methods. Code is available at https://github.com/LiJunnan1992/DivideMix .

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 2 code samples harvested from 1 repository linked to this paper: 0 ran · 2 unverified.

By repository: official repository: 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

LiJunnan1992/DivideMix officialmentioned in paperpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
jyansir/text2tree mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ACL Anthology id 2023.findings-emnlp.517 (that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 0 ran · 2 unverified. 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.

2unverified

Licence: 2 of the 2 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 LiJunnan1992/DivideMix. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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 “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.

LiJunnan1992/DivideMix official repository 2 samples, 0 ran · 2 unverified
eval_train in 10 papers Train_cifar.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 8a2d14d95795c655 · report
linear_rampup in 33 papers Train_cifar.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 767f49a34c3cb79a · report

Tasks

Image ClassificationLearning with noisy labels

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Clothing1M DivideMix Accuracy 74.76% #15 of 51 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (Inception-ResNet-v2) ImageNet Top-1 Accuracy 75.20 #31 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (Inception-ResNet-v2) ImageNet Top-5 Accuracy 91.64 #31 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (Inception-ResNet-v2) Top-1 Accuracy 77.32 #31 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (Inception-ResNet-v2) Top-5 Accuracy 91.64 #31 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (ResNet-50) ImageNet Top-1 Accuracy 74.42 ±0.29 #33 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (ResNet-50) ImageNet Top-5 Accuracy 91.21 ±0.12 #33 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (ResNet-50) Top-1 Accuracy 76.32 ±0.36 #33 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (ResNet-50) Top-5 Accuracy 90.65 ±0.16 #33 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix (ResNet-18) Top-1 Accuracy 76.08 #34 of 47 Archive leaderboard report
Learning with noisy labels CIFAR-100N Divide-Mix Accuracy (mean) 71.13 #4 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Aggregate Divide-Mix Accuracy (mean) 95.01 #7 of 26 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random1 Divide-Mix Accuracy (mean) 90.18 #14 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random2 Divide-Mix Accuracy (mean) 90.90 #8 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random3 Divide-Mix Accuracy (mean) 89.97 #12 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Worst Divide-Mix Accuracy (mean) 92.56 #6 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