Papers › Self-Supervised Learning for Large-Scale Unsupervised Image Clustering

Self-Supervised Learning for Large-Scale Unsupervised Image Clustering

24 Aug 2020arXiv:2008.10312archive 2025-07-28

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

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is challenging, and even the best approaches show much weaker performance than their supervised counterparts. Self-supervised deep learning has become a strong instrument for representation learning in computer vision. However, those methods have not been evaluated in a fully unsupervised setting. In this paper, we propose a simple scheme for unsupervised classification based on self-supervised representations. We evaluate the proposed approach with several recent self-supervised methods showing that it achieves competitive results for ImageNet classification (39% accuracy on ImageNet with 1000 clusters and 46% with overclustering). We suggest adding the unsupervised evaluation to a set of standard benchmarks for self-supervised learning. The code is available at https://github.com/Randl/kmeans_selfsuper

PaperPDFCodeCode 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 11 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 8 ran (6 with no instrument failure; 2 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 8 samples that ran have no recorded date.

Randl/kmeans_selfsuper officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 8 ran (2 instrument-failed) · 3 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

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 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.

2ran · our draft was wrong
6ran
3unverified

Licence: 0 of the 11 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 Randl/kmeans_selfsuper. “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.

Randl/kmeans_selfsuper official repository 11 samples, 8 ran (2 instrument-failed) · 3 unverified
crop_center_and_resize generate_prediction_tf.py ran MIT (permissive) · 74f9e58e15186552 · report fixture: signature img:EagerTensor/3/float, size:int/0/int, scale:float/0/float · returned EagerTensor · level recorded 2026-09-25
get_best_clusters cluster.py ran · our draft was wrong fingerprinted MIT (permissive) · 63dc243289400452 · report fixture: signature C:ndarray/2/float, k:int/0/int · returned ndarray · level recorded, date not recorded
get_cost_matrix in 6 papers cluster.py ran · our draft was wrong MIT (permissive) · 53437473e6a66a64 · report fixture: signature y_pred:ndarray/1/int, y:ndarray/1/int, nc:int/0/int · returned ndarray · level recorded, date not recorded
get_label in 36 papers generate_prediction_tf.py ran MIT (permissive) · c3d1c7b673f0c808 · report fixture: signature file_path:EagerTensor/0/<dtype: 'string'> · returned EagerTensor · level recorded 2026-09-25
get_label_objectnet generate_prediction_tf.py ran MIT (permissive) · 25b6cb1de2b6763b · report fixture: signature file_path:EagerTensor/0/<dtype: 'string'> · returned EagerTensor · level recorded 2026-09-25
inception_preproccess torch_utils.py ran MIT (permissive) · de53820d0a106f94 · report fixture: signature input_size:int/0/int, normalize:dict/0/? · returned Compose · level recorded 2026-09-25
scale_crop torch_utils.py ran MIT (permissive) · 8ed66ef9fef840b5 · report fixture: signature input_size:int/0/int, scale_size:int/0/int, normalize:dict/0/? · returned Compose · level recorded 2026-09-25
woof_preproccess torch_utils.py ran MIT (permissive) · f68937364f9c7540 · report fixture: returned Compose · level recorded 2026-09-25
eval in 90 papers generate_prediction_pytorch.py unverified MIT (permissive) · 96c98a6eaa49160b · report
eval in 90 papers generate_prediction_pytorch_supervised.py unverified MIT (permissive) · 526bad0a33805d03 · report
eval_swav generate_prediction_pytorch.py unverified MIT (permissive) · 9f240baca01dbd55 · report

Tasks

ClusteringGeneral ClassificationImage ClassificationImage ClusteringRepresentation LearningSelf-Supervised LearningUnsupervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ObjectNet BigBiGAN (RevNet-50 4×) Top-1 Accuracy 4.92 #105 of 106 Archive leaderboard report
Unsupervised Image Classification ImageNet SimCLRv2 ResNet-152 + SK (PCA+k-means, 1500 clusters) ARI 23.94±0.16 #3 of 9 Archive leaderboard report
Unsupervised Image Classification ImageNet SimCLRv2 ResNet-152 + SK (PCA+k-means, 1500 clusters) Accuracy (%) 46.03±0.21 #3 of 9 Archive leaderboard report
Unsupervised Image Classification ImageNet SimCLRv2 ResNet-152 + SK (PCA+k-means) ARI 22.80±0.60 #8 of 9 Archive leaderboard report
Unsupervised Image Classification ImageNet SimCLRv2 ResNet-152 + SK (PCA+k-means) Accuracy (%) 39.07±0.61 #8 of 9 Archive leaderboard report
Unsupervised Image Classification ObjectNet InfoMin ResNeXt-152 + SK (PCA+k-means) ARI 1.59±0.04 #1 of 2 Archive leaderboard report
Unsupervised Image Classification ObjectNet InfoMin ResNeXt-152 + SK (PCA+k-means) Accuracy (%) 6.53±0.19 #1 of 2 Archive leaderboard report
Unsupervised Image Classification ObjectNet SimCLRv2 ResNet-152 + SK (PCA+k-means, 1500 clusters) ARI 1.32±0.05 #2 of 2 Archive leaderboard report
Unsupervised Image Classification ObjectNet SimCLRv2 ResNet-152 + SK (PCA+k-means, 1500 clusters) Accuracy (%) 6.47±0.07 #2 of 2 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