Papers › Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels

Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels

25 Mar 2021arXiv:2103.13646archive 2025-07-28

Evgenii Zheltonozhskii, Chaim Baskin, Avi Mendelson, Alex M. Bronstein, Or Litany

The success of learning with noisy labels (LNL) methods relies heavily on the success of a warm-up stage where standard supervised training is performed using the full (noisy) training set. In this paper, we identify a "warm-up obstacle": the inability of standard warm-up stages to train high quality feature extractors and avert memorization of noisy labels. We propose "Contrast to Divide" (C2D), a simple framework that solves this problem by pre-training the feature extractor in a self-supervised fashion. Using self-supervised pre-training boosts the performance of existing LNL approaches by drastically reducing the warm-up stage's susceptibility to noise level, shortening its duration, and improving extracted feature quality. C2D works out of the box with existing methods and demonstrates markedly improved performance, especially in the high noise regime, where we get a boost of more than 27% for CIFAR-100 with 90% noise over the previous state of the art. In real-life noise settings, C2D trained on mini-WebVision outperforms previous works both in WebVision and ImageNet validation sets by 3% top-1 accuracy. We perform an in-depth analysis of the framework, including investigating the performance of different pre-training approaches and estimating the effective upper bound of the LNL performance with semi-supervised learning. Code for reproducing our experiments is available at https://github.com/ContrastToDivide/C2D

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 7 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 6 ran (3 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ContrastToDivide/C2D officialmentioned in paperpytorchSyntology: 7 samples, 6 ran (3 instrument-failed) · 1 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

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran; the contract check could not run
1ran
1unverified

Licence: 0 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 ContrastToDivide/C2D. “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.

ContrastToDivide/C2D official repository 7 samples, 6 ran (3 instrument-failed) · 1 unverified
CrossEntropyLoss in 6 papers cross_entropy.py ran · metamorphic tier: invariant MIT (permissive) · 0f9f54d5a814968a · report fixture: signature input:Tensor/2/float, target:Tensor/1/int · returned Tensor · level recorded 2026-09-22
_is_long cross_entropy.py ran · violated contract MIT (permissive) · 1fa7bb764f450073 · report fixture: signature x:Tensor/1/int · returned bool · level recorded 2026-09-22
cross_entropy in 92 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
cross_entropy.py ran; the contract check could not run (RAISES) MIT (permissive) · a8fa6f956d6f3de1 · report fixture: signature logits:Tensor/2/float, target:Tensor/1/int, weight:Tensor/1/float, ignore_index:int/0/int, reduction:str/0/str, smooth_eps:float/0/float · returned Tensor · level recorded 2026-09-22
linear_rampup in 33 papers main_cifar.py ran · honoured contract fingerprinted MIT (permissive) · 6944acdaa94d65ef · report fixture: signature current:int/0/int, warm_up:int/0/int, lambda_u:float/0/float, rampup_length:int/0/int · returned float · level recorded 2026-09-22
onehot in 39 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
cross_entropy.py ran · our draft was wrong MIT (permissive) · cfcd370121d1305f · report fixture: signature indexes:Tensor/1/int, N:NoneType/0/?, ignore_index:NoneType/0/? · returned Tensor · level recorded 2026-09-22
smoothing in 6 papers cross_entropy.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 46e004362de7a8d3 · report fixture: signature out:Tensor/2/float, y:Tensor/1/int, smooth_eps:float/0/float · returned Tensor · level recorded 2026-09-22
linear_rampup in 33 papers Train_webvision.py unverified MIT (permissive) · 371eb42215de99b0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for C2D (graph method: C2D). 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. CrossEntropyLoss entry · level 1 · ran · 0f9f54d5a814968a
  2. cross_entropy loss · level 1 · ran; the contract check could not run (RAISES) · a8fa6f956d6f3de1
  3. _is_long helper · level 1 · ran · violated contract · 1fa7bb764f450073
  4. smoothing helper · level 1 · ran; the contract check could not run (RAISES) · 46e004362de7a8d3
  5. onehot helper · level 1 · ran · our draft was wrong · cfcd370121d1305f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2103.13646") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationLearning with noisy labelsMemorization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 (with noisy labels) C2D (ELR+ with SimCLR, ResNet-34) Accuracy (under 20% Sym. label noise) 96.74 ± 0.12 #2 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (ELR+ with SimCLR, ResNet-34) Accuracy (under 50% Sym. label noise) 95.55 ± 0.32 #2 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (ELR+ with SimCLR, ResNet-34) Accuracy (under 80% Sym. label noise) 93.11 ± 0.70 #2 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (ELR+ with SimCLR, ResNet-34) Accuracy (under 90% Sym. label noise) 89.30 ± 0.21 #2 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (ELR+ with SimCLR, ResNet-34) Accuracy (under 95% Sym. label noise) 80.21 ± 1.91 #2 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (DivideMix with SimCLR, ResNet-18) Accuracy (under 20% Sym. label noise) 96.23 ± 0.09 #4 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (DivideMix with SimCLR, ResNet-18) Accuracy (under 50% Sym. label noise) 95.15 ± 0.16 #4 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (DivideMix with SimCLR, ResNet-18) Accuracy (under 80% Sym. label noise) 94.30 ± 0.12 #4 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (DivideMix with SimCLR, ResNet-18) Accuracy (under 90% Sym. label noise) 93.42 ± 0.09 #4 of 4 Archive leaderboard report
Image Classification CIFAR-10 (with noisy labels) C2D (DivideMix with SimCLR, ResNet-18) Accuracy (under 95% Sym. label noise) 87.72 ± 2.21 #4 of 4 Archive leaderboard report
Image Classification Clothing1M ELR+ with C2D (ResNet-50) Accuracy 74.58 ± 0.15% #17 of 51 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix with C2D (ResNet-50) ImageNet Top-1 Accuracy 78.57 ± 0.37 #14 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix with C2D (ResNet-50) ImageNet Top-5 Accuracy 93.04 ± 0.10 #14 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix with C2D (ResNet-50) Top-1 Accuracy 79.42 ± 0.34 #14 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 DivideMix with C2D (ResNet-50) Top-5 Accuracy 92.32 ± 0.33 #14 of 47 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