EUVIMEDEUVIMED entdecken
Crossref

Learning Common Semantics via Optimal Transport for Contrastive Multi-View Clustering

Qian Zhang, Lin Zhang, Ran Song, Runmin Cong, Yonghuai Liu, Wei Zhang

IEEE Transactions on Image Processing · 2024 · 33 · 4501-4515

DOI: 10.1109/tip.2024.3436615 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Qian Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science and Technology Major Project, Shandong Excellent Young Scientists Fund Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-view clustering aims to learn discriminative representations from multi-view data. Although existing methods show impressive performance by leveraging contrastive learning to tackle the representation gap between every two views, they share the common limitation of not performing semantic alignment from a global perspective, resulting in the undermining of semantic patterns in multi-view data. This paper presents CSOT, namely Common Semantics via Optimal Transport, to boost contrastive multi-view clustering via semantic learning in a common space that integrates all views. Through optimal transport, the samples in multiple views are mapped to the joint clusters which represent the multi-view semantic patterns in the common space. With the semantic assignment derived from the optimal transport plan, we design a semantic learning module where the soft assignment vector works as a global supervision to enforce the model to learn consistent semantics among all views. Moreover, we propose a semantic-aware re-weighting strategy to treat samples differently according to their semantic significance, which improves the effectiveness of cross-view contrastive representation learning. Extensive experimental results demonstrate that CSOT achieves the state-of-the-art clustering performance.

Förderung

  • National Natural Science Foundation of China
  • National Science and Technology Major Project
  • Shandong Excellent Young Scientists Fund Program
  • Young Taishan Scholars Program of Shandong Province
  • Project for Self-Developed Innovation Team of Jinan City

Zitieren

APA

Zhang, Q., Zhang, L., Song, R., Cong, R., Liu, Y., & Zhang, W. (2024). Learning Common Semantics via Optimal Transport for Contrastive Multi-View Clustering. IEEE Transactions on Image Processing, 33, 4501-4515. https://doi.org/10.1109/tip.2024.3436615

Vancouver

Zhang Q, Zhang L, Song R, Cong R, Liu Y, Zhang W. Learning Common Semantics via Optimal Transport for Contrastive Multi-View Clustering. IEEE Transactions on Image Processing. 2024;33:4501-4515. doi:10.1109/tip.2024.3436615

BibTeX
@article{Zhang2024,
  author = {Zhang, Qian and Zhang, Lin and Song, Ran and Cong, Runmin and Liu, Yonghuai and Zhang, Wei},
  title = {Learning Common Semantics via Optimal Transport for Contrastive Multi-View Clustering},
  journal = {IEEE Transactions on Image Processing},
  year = {2024},
  volume = {33},
  pages = {4501--4515},
  doi = {10.1109/tip.2024.3436615}
}
Kostenlos starten →