Dual Contrast-Driven Deep Multi-View Clustering
IEEE Transactions on Image Processing · 2024 · 33 · 4753-4764
DOI: 10.1109/tip.2024.3444269 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Jinrong Cui und 3 weiteren Autor:innen. Die Arbeit wurde bisher 98-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation.
Abstract (Originalsprache)
Consensus representation learning is one of the most popular approaches in the field of multi-view clustering. However, most of the existing methods cannot learn discriminative representations with a clustering-friendly structure since these methods ignore the separation among clusters and the compactness within each cluster. To tackle this issue, we propose a new deep multi-view clustering network with a dual contrastive mechanism to learn clustering-friendly representations. Specifically, our method employs dual contrasting losses: a dynamic cluster diffusion loss to maximize the distance between different clusters and a reliable neighbor-guided positive alignment loss to enhance compactness within each cluster. Our approach includes several key components: view-specific encoders to extract high-level features from each view, and an adaptive feature fusion strategy to obtain consensus representations across multiple views. The dynamic cluster diffusion module ensures inter-cluster separation by maximizing distances between different clusters in the consensus feature space. Simultaneously, the reliable neighbor-guided positive alignment module improves within-cluster compactness through a pseudo-label and nearest neighbor structure-driven contrastive loss. Experimental results on several datasets show that our method can acquire clustering-friendly representations with both good properties of inter-cluster separation and within-cluster compactness, and outperforms the existing state-of-the-art approaches in clustering performance. Our source code is available at https://github.com/tweety1028/DCMVC.
Förderung
- National Natural Science Foundation of China
- Guangdong Basic and Applied Basic Research Foundation
Zitieren
APA
Cui, J., Li, Y., Huang, H., & Wen, J. (2024). Dual Contrast-Driven Deep Multi-View Clustering. IEEE Transactions on Image Processing, 33, 4753-4764. https://doi.org/10.1109/tip.2024.3444269
Vancouver
Cui J, Li Y, Huang H, Wen J. Dual Contrast-Driven Deep Multi-View Clustering. IEEE Transactions on Image Processing. 2024;33:4753-4764. doi:10.1109/tip.2024.3444269
BibTeX
@article{Cui2024,
author = {Cui, Jinrong and Li, Yuting and Huang, Han and Wen, Jie},
title = {Dual Contrast-Driven Deep Multi-View Clustering},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {4753--4764},
doi = {10.1109/tip.2024.3444269}
}
EUVIMED