Papers › Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization

Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization

20 Apr 2017ICCV 2017 10arXiv:1704.06327archive 2025-07-28

Kamran Ghasedi Dizaji, Amirhossein Herandi, Cheng Deng, Weidong Cai, Heng Huang

Image clustering is one of the most important computer vision applications, which has been extensively studied in literature. However, current clustering methods mostly suffer from lack of efficiency and scalability when dealing with large-scale and high-dimensional data. In this paper, we propose a new clustering model, called DEeP Embedded RegularIzed ClusTering (DEPICT), which efficiently maps data into a discriminative embedding subspace and precisely predicts cluster assignments. DEPICT generally consists of a multinomial logistic regression function stacked on top of a multi-layer convolutional autoencoder. We define a clustering objective function using relative entropy (KL divergence) minimization, regularized by a prior for the frequency of cluster assignments. An alternating strategy is then derived to optimize the objective by updating parameters and estimating cluster assignments. Furthermore, we employ the reconstruction loss functions in our autoencoder, as a data-dependent regularization term, to prevent the deep embedding function from overfitting. In order to benefit from end-to-end optimization and eliminate the necessity for layer-wise pretraining, we introduce a joint learning framework to minimize the unified clustering and reconstruction loss functions together and train all network layers simultaneously. Experimental results indicate the superiority and faster running time of DEPICT in real-world clustering tasks, where no labeled data is available for hyper-parameter tuning.

PaperPDFConference PDFCode

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

Code

herandy/DEPICT officialmentioned in papermentioned on GitHub 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 CMU-PIE DEPICT Accuracy 0.850 #2 of 4 Archive leaderboard report
Image Clustering CMU-PIE DEPICT NMI 0.964 #2 of 4 Archive leaderboard report
Image Clustering CUB Birds DEPICT-Large Accuracy 0.061 #2 of 4 Archive leaderboard report
Image Clustering CUB Birds DEPICT-Large NMI 0.297 #2 of 4 Archive leaderboard report
Image Clustering CUB Birds DEPICT Accuracy 0.061 #3 of 4 Archive leaderboard report
Image Clustering CUB Birds DEPICT NMI 0.290 #3 of 4 Archive leaderboard report
Image Clustering FRGC DEPICT Accuracy 0.432 #1 of 3 Archive leaderboard report
Image Clustering FRGC DEPICT NMI 0.583 #1 of 3 Archive leaderboard report
Image Clustering Stanford Cars DEPICT Accuracy 0.063 #3 of 5 Archive leaderboard report
Image Clustering Stanford Cars DEPICT NMI 0.329 #3 of 5 Archive leaderboard report
Image Clustering Stanford Cars DEPICT-Large Accuracy 0.062 #4 of 5 Archive leaderboard report
Image Clustering Stanford Cars DEPICT-Large NMI 0.330 #4 of 5 Archive leaderboard report
Image Clustering Stanford Dogs DEPICT-Large Accuracy 0.054 #2 of 4 Archive leaderboard report
Image Clustering Stanford Dogs DEPICT-Large NMI 0.183 #2 of 4 Archive leaderboard report
Image Clustering Stanford Dogs DEPICT Accuracy 0.052 #3 of 4 Archive leaderboard report
Image Clustering Stanford Dogs DEPICT NMI 0.182 #3 of 4 Archive leaderboard report
Image Clustering YouTube Faces DB DEPICT Accuracy 0.611 #3 of 4 Archive leaderboard report
Image Clustering YouTube Faces DB DEPICT NMI 0.802 #3 of 4 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