Papers › Deep Multimodal Subspace Clustering Networks

Deep Multimodal Subspace Clustering Networks

17 Apr 2018arXiv:1804.06498archive 2025-07-28

Mahdi Abavisani, Vishal M. Patel

We present convolutional neural network (CNN) based approaches for unsupervised multimodal subspace clustering. The proposed framework consists of three main stages - multimodal encoder, self-expressive layer, and multimodal decoder. The encoder takes multimodal data as input and fuses them to a latent space representation. The self-expressive layer is responsible for enforcing the self-expressiveness property and acquiring an affinity matrix corresponding to the data points. The decoder reconstructs the original input data. The network uses the distance between the decoder's reconstruction and the original input in its training. We investigate early, late and intermediate fusion techniques and propose three different encoders corresponding to them for spatial fusion. The self-expressive layers and multimodal decoders are essentially the same for different spatial fusion-based approaches. In addition to various spatial fusion-based methods, an affinity fusion-based network is also proposed in which the self-expressive layer corresponding to different modalities is enforced to be the same. Extensive experiments on three datasets show that the proposed methods significantly outperform the state-of-the-art multimodal subspace clustering methods.

Paper PDF Code

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

Code

mahdiabavisani/Deep-multimodal-subspace-clustering-networks officialmentioned in papertf 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

Clustering Decoder Image Clustering Multi-modal Subspace Clustering Multi-view Subspace Clustering Multiview Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Clustering	ARL Polarimetric Thermal Face Dataset	DMSC	Accuracy	0.983	#1 of 1	Archive leaderboard	report
Image Clustering	Extended Yale-B	DMSC	Accuracy	0.992	#1 of 9	Archive leaderboard	report
Image Clustering	Extended Yale-B	DMSC	NMI	0.988	#1 of 9	Archive leaderboard	report
Image Clustering	USPS	DMSC	Accuracy	0.951	#7 of 16	Archive leaderboard	report
Image Clustering	USPS	DMSC	NMI	0.929	#7 of 16	Archive leaderboard	report
Multi-view Subspace Clustering	ARL Polarimetric Thermal Face Dataset	DMSC	Accuracy	0.988	#1 of 1	Archive leaderboard	report
Multi-view Subspace Clustering	ORL	DMSC	Accuracy	0.833	#2 of 3	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