</> Code with Papers by Syntology

Papers › Deep Comprehensive Correlation Mining for Image Clustering

Deep Comprehensive Correlation Mining for Image Clustering

15 Apr 2019ICCV 2019 10arXiv:1904.06925archive 2025-07-28

Jianlong Wu, Keyu Long, Fei Wang, Chen Qian, Cheng Li, Zhouchen Lin, Hongbin Zha

Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data. These deep clustering methods mainly focus on the correlation among samples, e.g., selecting high precision pairs to gradually tune the feature representation, which neglects other useful correlations. In this paper, we propose a novel clustering framework, named deep comprehensive correlation mining(DCCM), for exploring and taking full advantage of various kinds of correlations behind the unlabeled data from three aspects: 1) Instead of only using pair-wise information, pseudo-label supervision is proposed to investigate category information and learn discriminative features. 2) The features' robustness to image transformation of input space is fully explored, which benefits the network learning and significantly improves the performance. 3) The triplet mutual information among features is presented for clustering problem to lift the recently discovered instance-level deep mutual information to a triplet-level formation, which further helps to learn more discriminative features. Extensive experiments on several challenging datasets show that our method achieves good performance, e.g., attaining 62.3% clustering accuracy on CIFAR-10, which is 10.1% higher than the state-of-the-art results.

PaperPDFConference PDFCode

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

Code

Cory-M/DCCM officialmentioned in papermentioned on GitHubpytorchGPL-3.0 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

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

Tasks

ClusteringDeep ClusteringImage ClusteringPseudo Label

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 DCCM ARI 0.408 #31 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCCM Accuracy 0.623 #31 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCCM Backbone AlexNet #31 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCCM NMI 0.496 #31 of 40 Archive leaderboard report
Image Clustering CIFAR-10 DCCM Train set Train+Test #31 of 40 Archive leaderboard report
Image Clustering CIFAR-100 DCCM Accuracy 0.327 #23 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DCCM NMI 0.285 #23 of 30 Archive leaderboard report
Image Clustering CIFAR-100 DCCM Train Set Train+Test #23 of 30 Archive leaderboard report
Image Clustering ImageNet-10 DCCM Accuracy 0.71 #13 of 18 Archive leaderboard report
Image Clustering ImageNet-10 DCCM NMI 0.608 #13 of 18 Archive leaderboard report
Image Clustering Imagenet-dog-15 DCCM Accuracy 0.383 #14 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 DCCM NMI 0.321 #14 of 20 Archive leaderboard report
Image Clustering STL-10 DCCM Accuracy 0.482 #24 of 29 Archive leaderboard report
Image Clustering STL-10 DCCM Backbone AlexNet #24 of 29 Archive leaderboard report
Image Clustering STL-10 DCCM NMI 0.376 #24 of 29 Archive leaderboard report
Image Clustering STL-10 DCCM Train Split Train+Test #24 of 29 Archive leaderboard report
Image Clustering Tiny-ImageNet DCCM Accuracy 0.108 #9 of 14 Archive leaderboard report
Image Clustering Tiny-ImageNet DCCM NMI 0.224 #9 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