Papers › Deep Density-based Image Clustering

Deep Density-based Image Clustering

11 Dec 2018arXiv:1812.04287archive 2025-07-28

Yazhou Ren, Ni Wang, Mingxia Li, Zenglin Xu

Recently, deep clustering, which is able to perform feature learning that favors clustering tasks via deep neural networks, has achieved remarkable performance in image clustering applications. However, the existing deep clustering algorithms generally need the number of clusters in advance, which is usually unknown in real-world tasks. In addition, the initial cluster centers in the learned feature space are generated by k-means. This only works well on spherical clusters and probably leads to unstable clustering results. In this paper, we propose a two-stage deep density-based image clustering (DDC) framework to address these issues. The first stage is to train a deep convolutional autoencoder (CAE) to extract low-dimensional feature representations from high-dimensional image data, and then apply t-SNE to further reduce the data to a 2-dimensional space favoring density-based clustering algorithms. The second stage is to apply the developed density-based clustering technique on the 2-dimensional embedded data to automatically recognize an appropriate number of clusters with arbitrary shapes. Concretely, a number of local clusters are generated to capture the local structures of clusters, and then are merged via their density relationship to form the final clustering result. Experiments demonstrate that the proposed DDC achieves comparable or even better clustering performance than state-of-the-art deep clustering methods, even though the number of clusters is not given.

PaperPDFCode

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

Code

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 Fashion-MNIST DDC Accuracy 0.619 #9 of 13 Archive leaderboard report
Image Clustering Fashion-MNIST DDC NMI 0.682 #9 of 13 Archive leaderboard report
Image Clustering Fashion-MNIST DDC-DA Accuracy 0.609 #11 of 13 Archive leaderboard report
Image Clustering Fashion-MNIST DDC-DA NMI 0.661 #11 of 13 Archive leaderboard report
Image Clustering LetterA-J DDC-DA Accuracy 0.691 #1 of 2 Archive leaderboard report
Image Clustering LetterA-J DDC-DA NMI 0.629 #1 of 2 Archive leaderboard report
Image Clustering LetterA-J DDC Accuracy 0.573 #2 of 2 Archive leaderboard report
Image Clustering LetterA-J DDC NMI 0.546 #2 of 2 Archive leaderboard report
Image Clustering MNIST-full DDC-DA Accuracy 0.986 #5 of 16 Archive leaderboard report
Image Clustering MNIST-full DDC-DA NMI 0.961 #5 of 16 Archive leaderboard report
Image Clustering MNIST-test DDC-DA Accuracy 0.97 #3 of 11 Archive leaderboard report
Image Clustering MNIST-test DDC-DA NMI 0.927 #3 of 11 Archive leaderboard report
Image Clustering MNIST-test DDC Accuracy 0.965 #5 of 11 Archive leaderboard report
Image Clustering MNIST-test DDC NMI 0.916 #5 of 11 Archive leaderboard report
Image Clustering USPS DDC-DA Accuracy 0.977 #4 of 16 Archive leaderboard report
Image Clustering USPS DDC-DA NMI 0.939 #4 of 16 Archive leaderboard report
Image Clustering USPS DDC Accuracy 0.967 #8 of 16 Archive leaderboard report
Image Clustering USPS DDC NMI 0.918 #8 of 16 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