Papers › Self-labelling via simultaneous clustering and representation learning

Self-labelling via simultaneous clustering and representation learning

13 Nov 2019ICLR 2020 1arXiv:1911.05371archive 2025-07-28

Yuki Markus Asano, Christian Rupprecht, Andrea Vedaldi

Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks. However, doing so naively leads to ill posed learning problems with degenerate solutions. In this paper, we propose a novel and principled learning formulation that addresses these issues. The method is obtained by maximizing the information between labels and input data indices. We show that this criterion extends standard crossentropy minimization to an optimal transport problem, which we solve efficiently for millions of input images and thousands of labels using a fast variant of the Sinkhorn-Knopp algorithm. The resulting method is able to self-label visual data so as to train highly competitive image representations without manual labels. Our method achieves state of the art representation learning performance for AlexNet and ResNet-50 on SVHN, CIFAR-10, CIFAR-100 and ImageNet and yields the first self-supervised AlexNet that outperforms the supervised Pascal VOC detection baseline. Code and models are available.

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="1911.05371")

Code

Syntology Ran 7 of 18 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 4 ran; community (archive-listed): 1 sample from 1 repository, 1 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yukimasano/self-label officialmentioned in paperpytorchMIT report
ananyahjha93/swav mentioned on GitHubpytorchNOASSERTION report
hsfzxjy/swavx mentioned on GitHubpytorch report
mingu6/action_seg_ot mentioned on GitHubpytorch report
vinhdv1628/image_classification_task mentioned on GitHubpytorchNOASSERTION 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

18 samples harvested; 7 ran; 0 honoured the contract we drafted; 11 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.

4ran · our draft was wrong
3ran
11unverified

Licence: 3 of the 18 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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

conv3x3 yukimasano/self-label/models/resnetv1.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
get_model_device yukimasano/self-label/files.py official repository ran MIT (permissive) · 5a0beb315ee2d6b3 · report
resnet18 yukimasano/self-label/models/resnetv1.py official repository ran MIT (permissive) · b073ea484dc3837e · report
resnet34 yukimasano/self-label/models/resnetv1.py official repository ran MIT (permissive) · 5edd587f0ca09bf9 · report
PreActResNet50 yukimasano/self-label/models/resnetv2.py official repository unverified MIT (permissive) · e43df98524d81ee5 · report
alexnet yukimasano/self-label/models/alexnet.py official repository unverified MIT (permissive) · eab58619dff18322 · report
get_aug_dataloader yukimasano/self-label/data.py official repository unverified MIT (permissive) · 3a5443dcfa195e32 · report
get_standard_data_loader yukimasano/self-label/data.py official repository unverified MIT (permissive) · 225a04812784e2fd · report
gpu_mul_AB yukimasano/self-label/multigpu.py official repository unverified MIT (permissive) · 33bc9402815412a2 · report
gpu_mul_Ax yukimasano/self-label/multigpu.py official repository unverified MIT (permissive) · 7fea308d010604cb · report
kNN yukimasano/self-label/cifar_utils.py official repository unverified MIT (permissive) · d7bf5b70dddf2c9d · report
load_checkpoint yukimasano/self-label/files.py official repository unverified MIT (permissive) · 28ef548cecab7d06 · report
load_checkpoint_all yukimasano/self-label/files.py official repository unverified MIT (permissive) · b6f4e798c35df8ff · report
make_layers_features yukimasano/self-label/models/alexnet.py official repository unverified MIT (permissive) · 68d8bd2d7e4d0e88 · report
resnetv2 yukimasano/self-label/models/resnetv2.py official repository unverified MIT (permissive) · aa7ecec21e8b6217 · report
distributed_sinkhorn hsfzxjy/swavx/main_swav.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 103cb98c938400f1 · report
conv1x1 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · d9def42110729a85 · report
conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 160bb14bd76201b4 · report

Tasks

ClusteringContrastive LearningImage ClusteringRepresentation LearningSelf-Supervised Image ClassificationSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Contrastive Learning imagenet-1k ResNet50 ImageNet Top-1 Accuracy 61.5 #9 of 14 Archive leaderboard report
Image Clustering ImageNet SeLa Accuracy - #12 of 12 Archive leaderboard report
Image Clustering ImageNet SeLa NMI 66.4 #12 of 12 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (ResNet50) (arxiv 3) Number of Params 24M #119 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (ResNet50) (arxiv 3) Top 1 Accuracy 61.5% #119 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (ResNet50) (arxiv 3) Top 5 Accuracy 84.0% #119 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (ResNet50) Number of Params 24M #129 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (ResNet50) Top 1 Accuracy 55.7% #129 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (ResNet50) Top 5 Accuracy 79.5% #129 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (AlexNet) (arxiv v3) Number of Params 61M #133 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet SeLa (AlexNet) (arxiv v3) Top 1 Accuracy 50.0% #133 of 144 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

1x1 ConvolutionConvolutionDense ConnectionsDropoutGrouped ConvolutionLocal Response NormalizationMax PoolingReLUSoftmax

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