Papers › Deep Clustering for Unsupervised Learning of Visual Features

Deep Clustering for Unsupervised Learning of Visual Features

15 Jul 2018ECCV 2018 9arXiv:1807.05520archive 2025-07-28

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

Clustering is a class of unsupervised learning methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on large scale datasets. In this work, we present DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features. DeepCluster iteratively groups the features with a standard clustering algorithm, k-means, and uses the subsequent assignments as supervision to update the weights of the network. We apply DeepCluster to the unsupervised training of convolutional neural networks on large datasets like ImageNet and YFCC100M. The resulting model outperforms the current state of the art by a significant margin on all the standard benchmarks.

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="1807.05520")

Code

Syntology Ran 5 of 7 code samples harvested from 3 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: community (archive-listed): 7 samples from 3 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/deepcluster officialmentioned on GitHubpytorchNOASSERTION report
461054993/SDCN mentioned on GitHubpytorchApache-2.0 report
Confusezius/selfsupervised_learning mentioned on GitHubpytorch report
ananyahjha93/swav mentioned on GitHubpytorchNOASSERTION report
asanakoy/deep_clustering mentioned on GitHubpytorch report
bdy9527/SDCN mentioned on GitHubpytorch report
betashort/DeepClusterings mentioned on GitHubpytorch report
hsfzxjy/swavx 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

7 samples harvested; 5 ran; 0 honoured the contract we drafted; 2 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 · our draft was wrong
1ran · fixture could not drive it
3ran
2unverified

Licence: 4 of the 7 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

AE bdy9527/SDCN/sdcn.py community (archive-listed) ran Apache-2.0 (permissive) · c9adc6036aa45d3e · report
GNNLayer bdy9527/SDCN/sdcn.py community (archive-listed) ran Apache-2.0 (permissive) · 5c5c46d837a22ed0 · report
ReassignedDataset betashort/DeepClusterings/DeepClustering/deepcluster.py community (archive-listed) ran no licence file found · pointer only · 2ec706e9bf55a6df · report
cluster_assign betashort/DeepClusterings/DeepClustering/deepcluster.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 50c8238f31118570 · report
get_indices_sparse hsfzxjy/swavx/main_deepclusterv2.py community (archive-listed) ran · our draft was wrong fingerprinted licence not identified · pointer only · c2abbf3e8913b375 · report
SDCN bdy9527/SDCN/sdcn.py community (archive-listed) unverified Apache-2.0 (permissive) · 4aee3d437cd88960 · report
cluster_memory hsfzxjy/swavx/main_deepclusterv2.py community (archive-listed) unverified licence not identified · pointer only · 7a53b1371c3b1e7b · report

Tasks

ClusteringDeep ClusteringImage ClusteringSelf-Supervised Image ClassificationSemantic SegmentationUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 DeepCluster ARI - #34 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DeepCluster Accuracy 0.374 #34 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DeepCluster Backbone ResNet-34 #34 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DeepCluster NMI - #34 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DeepCluster Train set Train+Test #34 of 40 Archive leaderboard report
Image Clustering CIFAR-100 DeeperCluster Accuracy 0.189 #25 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DeeperCluster Train Set Train+Test #25 of 30 Archive leaderboard report
Self-Supervised Image Classification ImageNet DeepCluster (AlexNet) Number of Params 61M #138 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet DeepCluster (AlexNet) Top 1 Accuracy 41.0 #138 of 144 Archive leaderboard report
Unsupervised Semantic Segmentation Cityscapes test MDC Accuracy 40.7 #13 of 14 Archive leaderboard report
Unsupervised Semantic Segmentation Cityscapes test MDC mIoU 7.1 #13 of 14 Archive leaderboard report
Unsupervised Semantic Segmentation ImageNet-S-50 MDC (Supervised pretrain) mIoU (test) 14.3 #5 of 5 Archive leaderboard report
Unsupervised Semantic Segmentation ImageNet-S-50 MDC (Supervised pretrain) mIoU (val) 14.6 #5 of 5 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: DeepCluster

DeepClusterk-Means Clustering

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