Papers › Improving Unsupervised Image Clustering With Robust Learning

Improving Unsupervised Image Clustering With Robust Learning

21 Dec 2020CVPR 2021 1arXiv:2012.11150archive 2025-07-28

Sungwon Park, Sungwon Han, Sundong Kim, Danu Kim, Sungkyu Park, Seunghoon Hong, Meeyoung Cha

Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an innovative model RUC that is inspired by robust learning. RUC's novelty is at utilizing pseudo-labels of existing image clustering models as a noisy dataset that may include misclassified samples. Its retraining process can revise misaligned knowledge and alleviate the overconfidence problem in predictions. The model's flexible structure makes it possible to be used as an add-on module to other clustering methods and helps them achieve better performance on multiple datasets. Extensive experiments show that the proposed model can adjust the model confidence with better calibration and gain additional robustness against adversarial noise.

PaperPDFConference PDFCode

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

Code

deu30303/RUC 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

ClusteringImage ClusteringUnsupervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 RUC Accuracy 0.903 #13 of 40 Archive leaderboard report
Image Clustering CIFAR-10 RUC Backbone ResNet-18 #13 of 40 Archive leaderboard report
Image Clustering CIFAR-100 RUC Train Set Train #30 of 30 Archive leaderboard report
Image Clustering STL-10 RUC Accuracy 0.867 #9 of 29 Archive leaderboard report
Image Clustering STL-10 RUC Backbone ResNet-18 #9 of 29 Archive leaderboard report
Unsupervised Image Classification CIFAR-10 RUC Accuracy 90.3 #3 of 9 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 RUC Accuracy 54.3 #9 of 14 Archive leaderboard report
Unsupervised Image Classification STL-10 RUC Accuracy 86.7 #4 of 9 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