</> Code with Papers by Syntology

Papers › Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders

Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders

23 Mar 2017arXiv:1703.07980archive 2025-07-28

Fengfu Li, Hong Qiao, Bo Zhang, Xuanyang Xi

Traditional image clustering methods take a two-step approach, feature learning and clustering, sequentially. However, recent research results demonstrated that combining the separated phases in a unified framework and training them jointly can achieve a better performance. In this paper, we first introduce fully convolutional auto-encoders for image feature learning and then propose a unified clustering framework to learn image representations and cluster centers jointly based on a fully convolutional auto-encoder and soft k-means scores. At initial stages of the learning procedure, the representations extracted from the auto-encoder may not be very discriminative for latter clustering. We address this issue by adopting a boosted discriminative distribution, where high score assignments are highlighted and low score ones are de-emphasized. With the gradually boosted discrimination, clustering assignment scores are discriminated and cluster purities are enlarged. Experiments on several vision benchmark datasets show that our methods can achieve a state-of-the-art performance.

PaperPDFCode

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

Code

linqinghong/Deep-Clustering-Paper mentioned on GitHub report
waynezhanghk/gacluster mentioned on GitHubpytorchBSD-2-Clause 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 Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering Coil-20 DBC Accuracy 0.793 #4 of 6 Archive leaderboard report
Image Clustering Coil-20 DBC NMI 0.895 #4 of 6 Archive leaderboard report
Image Clustering MNIST-full DBC Accuracy 0.976 #10 of 16 Archive leaderboard report
Image Clustering MNIST-full DBC NMI 0.937 #10 of 16 Archive leaderboard report
Image Clustering USPS DBC Accuracy 0.743 #16 of 16 Archive leaderboard report
Image Clustering USPS DBC NMI 0.724 #16 of 16 Archive leaderboard report
Image Clustering coil-100 DBC Accuracy 0.775 #8 of 10 Archive leaderboard report
Image Clustering coil-100 DBC NMI 0.905 #8 of 10 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