Papers › Unsupervised Visual Representation Learning by Online Constrained K-Means

Unsupervised Visual Representation Learning by Online Constrained K-Means

24 May 2021CVPR 2022 1arXiv:2105.11527archive 2025-07-28

Qi Qian, Yuanhong Xu, Juhua Hu, Hao Li, Rong Jin

Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination. The main challenge resides in clustering since prevalent clustering methods (e.g., k-means) have to run in a batch mode. Besides, there can be a trivial solution consisting of a dominating cluster. To address these challenges, we first investigate the objective of clustering-based representation learning. Based on this, we propose a novel clustering-based pretext task with online \textbf{Co}nstrained \textbf{K}-m\textbf{e}ans (\textbf{CoKe}). Compared with the balanced clustering that each cluster has exactly the same size, we only constrain the minimal size of each cluster to flexibly capture the inherent data structure. More importantly, our online assignment method has a theoretical guarantee to approach the global optimum. By decoupling clustering and discrimination, CoKe can achieve competitive performance when optimizing with only a single view from each instance. Extensive experiments on ImageNet and other benchmark data sets verify both the efficacy and efficiency of our proposal. Code is available at \url{https://github.com/idstcv/CoKe}.

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="2105.11527")

Code

Syntology Ran 3 of 6 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · fixture could not drive it.

By repository: official repository: 6 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

idstcv/coke officialmentioned in paperpytorchApache-2.0 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

6 samples harvested; 3 ran; 1 honoured the contract we drafted; 3 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.

1ran · honoured contract
1ran · violated contract
1ran · fixture could not drive it
3unverified

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 idstcv/coke. “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.

accuracy idstcv/coke/eval_lincls.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 131a82fd65128218 · report
has_file_allowed_extension idstcv/coke/coke/folder.py official repository ran · violated contract Apache-2.0 (permissive) · c556c4f841693abe · report
validate idstcv/coke/eval_lincls.py official repository ran · honoured contract Apache-2.0 (permissive) · 5c22680084c0ea6f · report
concat_all_gather idstcv/coke/coke/builder_double_view.py official repository unverified Apache-2.0 (permissive) · 73cecca9f3575f09 · report
is_image_file idstcv/coke/coke/folder.py official repository unverified Apache-2.0 (permissive) · 10b3abf638e3b68c · report
make_dataset idstcv/coke/coke/folder.py official repository unverified Apache-2.0 (permissive) · b426c66097517bb9 · report

Tasks

ClusteringContrastive LearningImage ClusteringMetric LearningOnline ClusteringPseudo LabelRepresentation LearningSelf-Supervised Image ClassificationUnsupervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 CoKe ARI 0.732 #20 of 40 Archive leaderboard report
Image Clustering CIFAR-10 CoKe Accuracy 0.857 #20 of 40 Archive leaderboard report
Image Clustering CIFAR-10 CoKe Backbone ResNet-18 #20 of 40 Archive leaderboard report
Image Clustering CIFAR-10 CoKe NMI 0.766 #20 of 40 Archive leaderboard report
Image Clustering CIFAR-10 CoKe Train set Train #20 of 40 Archive leaderboard report
Self-Supervised Image Classification ImageNet CoKe (ResNet-50) Number of Params 25M #61 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet CoKe (ResNet-50) Top 1 Accuracy 76.4% #61 of 144 Archive leaderboard report
Unsupervised Image Classification CIFAR-10 CoKe Accuracy 85.7 #6 of 9 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 CoKe Accuracy 49.7 #12 of 14 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