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 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 18 code samples: 16 from 2 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 18: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); 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.

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

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 16 samples that ran have no recorded date.

yukimasano/self-label officialmentioned in paperpytorchMITSyntology: 15 samples, 13 ran (4 instrument-failed) · 2 unverified report
ananyahjha93/swav mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
hsfzxjy/swavx mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mingu6/action_seg_ot mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Action Segmentation: An Analysis of Modern Techniques (arXiv:2210.10352; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
vinhdv1628/image_classification_task mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 7 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
9ran
2unverified

Licence: 6 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples are listed last, in a group without a repository. “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.

yukimasano/self-label official repository 15 samples, 13 ran (4 instrument-failed) · 2 unverified
PreActResNet50 in 6 papers models/resnetv2.py ran MIT (permissive) · e43df98524d81ee5 · report fixture: signature num_classes:list/1/int · returned PreActResNet · level recorded 2026-09-25
alexnet in 42 papers models/alexnet.py ran MIT (permissive) · eab58619dff18322 · report fixture: signature bn:bool/0/bool, num_classes:list/1/int, init:bool/0/bool, size:str/0/str · returned AlexNet · level recorded 2026-09-25
conv3x3 in 1,376 papers models/resnetv1.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
get_aug_dataloader data.py ran MIT (permissive) · 3a5443dcfa195e32 · report fixture: signature image_dir:str/0/str, is_validation:bool/0/bool, batch_size:int/0/int, image_size:int/0/int, crop_size:int/0/int, mean:list/1/float, std:list/1/float, num_workers:int/0/int, augs:int/0/int, shuffle:bool/0/bool · returned DataLoader · level recorded 2026-09-25
get_model_device in 8 papers files.py ran · our draft was wrong MIT (permissive) · 5a0beb315ee2d6b3 · report fixture: signature model:callable/0/? · returned device · level recorded 2026-09-24
get_standard_data_loader data.py ran MIT (permissive) · 225a04812784e2fd · report fixture: signature image_dir:str/0/str, is_validation:bool/0/bool, batch_size:int/0/int, image_size:int/0/int, crop_size:int/0/int, mean:list/1/float, std:list/1/float, num_workers:int/0/int, no_random_crops:bool/0/bool, tencrops:bool/0/bool · returned DataLoader · level recorded 2026-09-25
gpu_mul_Ax multigpu.py ran MIT (permissive) · 7fea308d010604cb · report fixture: signature A:list/1/Tensor, b:Tensor/2/float, ngpu:int/0/int, splits:list/1/int, TYPE:dtype/0/?, model_gpus:int/0/int · returned Tensor · level recorded 2026-09-25
load_checkpoint in 277 papers files.py ran MIT (permissive) · 28ef548cecab7d06 · report fixture: signature checkpoint_dir:str/0/str, model:callable/0/?, optimizer:SGD/0/? · returned tuple · level recorded 2026-09-25
load_checkpoint_all files.py ran MIT (permissive) · b6f4e798c35df8ff · report fixture: signature checkpoint_dir:str/0/str, model:callable/0/?, opt:SGD/0/? · returned tuple · level recorded 2026-09-25
make_layers_features in 5 papers models/alexnet.py ran MIT (permissive) · 68d8bd2d7e4d0e88 · report fixture: signature cfg:list/1/tuple, input_dim:int/0/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-25
resnet18 in 432 papers models/resnetv1.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · b073ea484dc3837e · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers models/resnetv1.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 5edd587f0ca09bf9 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnetv2 models/resnetv2.py ran MIT (permissive) · aa7ecec21e8b6217 · report fixture: signature nlayers:int/0/int, num_classes:list/1/int, expansion:int/0/int · returned PreActResNet · level recorded 2026-09-25
gpu_mul_AB multigpu.py unverified MIT (permissive) · 33bc9402815412a2 · report
kNN cifar_utils.py unverified MIT (permissive) · d7bf5b70dddf2c9d · report
hsfzxjy/swavx community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
distributed_sinkhorn in 17 papers main_swav.py ran · our draft was wrong licence not identified · pointer only · 103cb98c938400f1 · report fixture: returned Tensor · level recorded 2026-09-22
Repository not located 2 samples, 2 ran (2 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
conv1x1 in 691 papers repository not located ran · our draft was wrong licence of this copy not recorded · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers repository not located ran · our draft was wrong licence of this copy not recorded · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded

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