Papers › Selective Pseudo-label Clustering

Selective Pseudo-label Clustering

22 Jul 2021arXiv:2107.10692archive 2025-07-28

Louis Mahon, Thomas Lukasiewicz

Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering techniques. As clustering is typically performed in a purely unsupervised setting, where no training labels are available, the question then arises as to how the DNN feature extractor can be trained. The most accurate existing approaches combine the training of the DNN with the clustering objective, so that information from the clustering process can be used to update the DNN to produce better features for clustering. One problem with this approach is that these ``pseudo-labels'' produced by the clustering algorithm are noisy, and any errors that they contain will hurt the training of the DNN. In this paper, we propose selective pseudo-label clustering, which uses only the most confident pseudo-labels for training the~DNN. We formally prove the performance gains under certain conditions. Applied to the task of image clustering, the new approach achieves a state-of-the-art performance on three popular image datasets. Code is available at https://github.com/Lou1sM/clustering.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Lou1sM/clustering officialmentioned in papermentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Clustering Image Clustering Pseudo Label

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Clustering	Fashion-MNIST	SPC	Accuracy	0.679	#3 of 13	Archive leaderboard	report
Image Clustering	Fashion-MNIST	SPC	NMI	0.735	#3 of 13	Archive leaderboard	report
Image Clustering	MNIST-full	SPC	Accuracy	0.992	#1 of 16	Archive leaderboard	report
Image Clustering	MNIST-full	SPC	NMI	0.975	#1 of 16	Archive leaderboard	report
Image Clustering	USPS	SPC	Accuracy	0.984	#1 of 16	Archive leaderboard	report
Image Clustering	USPS	SPC	NMI	0.954	#1 of 16	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