</> Code with Papers by Syntology

Papers › Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

5 Dec 2019arXiv:1912.02678archive 2025-07-28

Guy Shiran, Daphna Weinshall

The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an end-to-end fashion, providing direct cluster assignments of images without additional processing. Multi-Modal Deep Clustering (MMDC), trains a deep network to align its image embeddings with target points sampled from a Gaussian Mixture Model distribution. The cluster assignments are then determined by mixture component association of image embeddings. Simultaneously, the same deep network is trained to solve an additional self-supervised task of predicting image rotations. This pushes the network to learn more meaningful image representations that facilitate a better clustering. Experimental results show that MMDC achieves or exceeds state-of-the-art performance on six challenging benchmarks. On natural image datasets we improve on previous results with significant margins of up to 20% absolute accuracy points, yielding an accuracy of 82% on CIFAR-10, 45% on CIFAR-100 and 69% on STL-10.

PaperPDFCode

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

Code

guysrn/mmdc 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

ClusteringDeep ClusteringImage Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 MMDC Accuracy 0.820 #26 of 40 Archive leaderboard report
Image Clustering CIFAR-10 MMDC Backbone ResNet18 #26 of 40 Archive leaderboard report
Image Clustering CIFAR-10 MMDC NMI 0.703 #26 of 40 Archive leaderboard report
Image Clustering CIFAR-100 MMDC Accuracy 0.446 #18 of 30 Archive leaderboard report
Image Clustering CIFAR-100 MMDC NMI 0.418 #18 of 30 Archive leaderboard report
Image Clustering ImageNet-10 MMDC Accuracy 0.811 #12 of 18 Archive leaderboard report
Image Clustering ImageNet-10 MMDC NMI 0.719 #12 of 18 Archive leaderboard report
Image Clustering STL-10 MMDC Accuracy 0.694 #20 of 29 Archive leaderboard report
Image Clustering STL-10 MMDC Backbone ResNet18 #20 of 29 Archive leaderboard report
Image Clustering STL-10 MMDC NMI 0.593 #20 of 29 Archive leaderboard report
Image Clustering Tiny-ImageNet MMDC Accuracy 0.119 #8 of 14 Archive leaderboard report
Image Clustering Tiny-ImageNet MMDC NMI 0.274 #8 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