Papers › Big Self-Supervised Models are Strong Semi-Supervised Learners

Big Self-Supervised Models are Strong Semi-Supervised Learners

17 Jun 2020NeurIPS 2020 12arXiv:2006.10029archive 2025-07-28

Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, Geoffrey Hinton

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in a task-agnostic way, in contrast to common approaches to semi-supervised learning for computer vision, we show that it is surprisingly effective for semi-supervised learning on ImageNet. A key ingredient of our approach is the use of big (deep and wide) networks during pretraining and fine-tuning. We find that, the fewer the labels, the more this approach (task-agnostic use of unlabeled data) benefits from a bigger network. After fine-tuning, the big network can be further improved and distilled into a much smaller one with little loss in classification accuracy by using the unlabeled examples for a second time, but in a task-specific way. The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2, supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge. This procedure achieves 73.9% ImageNet top-1 accuracy with just 1% of the labels (≤13 labeled images per class) using ResNet-50, a 10× improvement in label efficiency over the previous state-of-the-art. With 10% of labels, ResNet-50 trained with our method achieves 77.5% top-1 accuracy, outperforming standard supervised training with all of the labels.

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

No sample from the archive's official repository (google-research/simclr) is linked to this paper; the 6 samples below come from 1 community repository. Syntology harvested code from google-research/simclr for another paper.

google-research/simclr: Syntology's graph links these samples to A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method.

Syntology 6 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 6 samples from 1 repository, 4 ran (4 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 6 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/simclr officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
mariaauslander/capstone_fall20_irrigation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
nikheelpandey/TAUP mentioned on GitHubpytorchSyntology: not harvested report
nikheelpandey/TAUP-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
parkinkon1/simclr mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
sayakpaul/PAWS-TF mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View... (arXiv:2104.13963; that paper's own run record: 19 ran (of which 4 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
serre-lab/prj_selfsup mentioned on GitHubtfApache-2.0Syntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
ta9ryuWalrus/simclr mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
lightly-ai/lightly pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Momentum Contrast for Unsupervised Visual Representation Learning (arXiv:1911.05722; that paper's own run record: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified), A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified), Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (arXiv:2006.09882; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified) and 8 more (every one in this page's JSON twin); 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

6 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 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 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.

4ran
2unverified

Licence: 0 of the 6 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 serre-lab/prj_selfsup. “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.

serre-lab/prj_selfsup community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
attractive_loss model/objective.py ran Apache-2.0 (permissive) · a7a5dcdaf8aafb54 · report fixture: signature hidden:SymbolicTensor/2/float, temperature:float/0/float, hidden_norm:bool/0/bool, weights:float/0/float · returned tuple · level recorded 2026-09-24
attractive_repulsive_loss model/objective.py ran Apache-2.0 (permissive) · 79e0efae44111eea · report fixture: signature hidden:SymbolicTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, tpu_context:NoneType/0/?, weights:float/0/float · returned tuple · level recorded 2026-09-24
resnet_autoencoder_v1_generator model/resnet_ae.py ran Apache-2.0 (permissive) · ac78dbf80b2d832a · report fixture: signature encoder:callable/0/?, decoder:callable/0/?, metric:callable/0/?, skip:bool/0/bool, mask_augs:float/0/float, greyscale_viz:bool/0/bool, data_format:str/0/str · returned function · level recorded 2026-09-24
supervised_loss model/objective.py ran Apache-2.0 (permissive) · e888c30f5b90e24a · report fixture: signature labels:SymbolicTensor/2/float, logits:SymbolicTensor/2/float, weights:SymbolicTensor/1/float · returned SymbolicTensor · level recorded 2026-09-24
get_train_steps in 5 papers model/model_util.py unverified Apache-2.0 (permissive) · 14ec8ff095316493 · report
learning_rate_schedule in 15 papers model/model_util.py unverified Apache-2.0 (permissive) · ea360af54446b02b · report

Tasks

Self-Supervised Image ClassificationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-152 x3, SK) Number of Params 795M #28 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-152 x3, SK) Top 1 Accuracy 79.8% #28 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-152 x3, SK) Top 5 Accuracy 94.9% #28 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-50 x2) Number of Params 94M #69 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-50 x2) Top 1 Accuracy 75.6% #69 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-50 x2) Top 5 Accuracy 92.7% #69 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-50) Number of Params 24M #97 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-50) Top 1 Accuracy 71.7% #97 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SimCLRv2 (ResNet-50) Top 5 Accuracy 90.4% #97 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimCLRv2 (ResNet-152, 3×+SK) Number of Params 795M #46 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) SimCLRv2 (ResNet-152, 3×+SK) Top 1 Accuracy 83.1% #46 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 self-distilled (ResNet-152 x3, SK) Top 1 Accuracy 76.6% #10 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 self-distilled (ResNet-152 x3, SK) Top 5 Accuracy 93.4% #10 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 distilled (ResNet-50 x2, SK) Top 1 Accuracy 75.9% #11 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 distilled (ResNet-50 x2, SK) Top 5 Accuracy 93.0% #11 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 (ResNet-152 x3, SK) Top 1 Accuracy 74.9% #13 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 (ResNet-152 x3, SK) Top 5 Accuracy 92.3% #13 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 distilled (ResNet-50) Top 1 Accuracy 73.9% #14 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 distilled (ResNet-50) Top 5 Accuracy 91.5% #14 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 (ResNet-50 ×2) Top 1 Accuracy 66.3% #30 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 (ResNet-50 ×2) Top 5 Accuracy 87.4% #30 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 (ResNet-50) Top 1 Accuracy 57.9% #42 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 1% labeled data SimCLRv2 (ResNet-50) Top 5 Accuracy 82.5% #42 of 65 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 self-distilled (ResNet-152 x3, SK) Top 1 Accuracy 80.9% #9 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 self-distilled (ResNet-152 x3, SK) Top 5 Accuracy 95.5% #9 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 distilled (ResNet-50 x2, SK) Top 1 Accuracy 80.2% #11 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 distilled (ResNet-50 x2, SK) Top 5 Accuracy 95.0% #11 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 (ResNet-152 x3, SK) Top 1 Accuracy 80.1% #12 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 (ResNet-152 x3, SK) Top 5 Accuracy 95.0% #12 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 distilled (ResNet-50) Top 1 Accuracy 77.5% #20 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 distilled (ResNet-50) Top 5 Accuracy 93.4% #20 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 (ResNet-50 x2) Top 1 Accuracy 73.9% #33 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 (ResNet-50 x2) Top 5 Accuracy 91.9% #33 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 (ResNet-50) Top 1 Accuracy 68.4% #43 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data SimCLRv2 (ResNet-50) Top 5 Accuracy 89.2% #43 of 75 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

Introduced by this paper: SimCLRv2

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSimCLRv2

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