Soft Neighbors Supported Contrastive Clustering
IEEE Transactions on Image Processing · 2025 · 34 · 4315-4327
DOI: 10.1109/tip.2025.3583194 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Yu Duan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Natural Science Basic Research Program of Shaanxi, National Natural Science Foundation of China.
Abstract (Originalsprache)
Existing deep clustering methods leverage contrastive or non-contrastive learning to facilitate downstream tasks. Most contrastive-based methods typically learn representations by comparing positive pairs (two views of the same sample) against negative pairs (views of different samples). However, we spot that this hard treatment of samples ignores inter-sample relationships, leading to class collisions and degrade clustering performances. In this paper, we propose a soft neighbor supported contrastive clustering method to address this issue. Specifically, we first introduce a concept called perception radius to quantify similarity confidence between a sample and its neighbors. Based on this insight, we design a two-level soft neighbor loss that captures both local and global neighborhood relationships. Additionally, a cluster-level loss enforces compact and well-separated cluster distributions. Finally, we conduct a pseudo-label refinement strategy to mitigate false negative samples. Extensive experiments on benchmark datasets demonstrate the superiority of our method. The code is available at https://github.com/DuannYu/soft-neighbors-supported-clustering.
Förderung
- National Key Research and Development Program of China
- Natural Science Basic Research Program of Shaanxi
- National Natural Science Foundation of China
Zitieren
APA
Duan, Y., Chen, H., Zhang, R., Wang, R., Nie, F., & Li, X. (2025). Soft Neighbors Supported Contrastive Clustering. IEEE Transactions on Image Processing, 34, 4315-4327. https://doi.org/10.1109/tip.2025.3583194
Vancouver
Duan Y, Chen H, Zhang R, Wang R, Nie F, Li X. Soft Neighbors Supported Contrastive Clustering. IEEE Transactions on Image Processing. 2025;34:4315-4327. doi:10.1109/tip.2025.3583194
BibTeX
@article{Duan2025,
author = {Duan, Yu and Chen, Huimin and Zhang, Runxin and Wang, Rong and Nie, Feiping and Li, Xuelong},
title = {Soft Neighbors Supported Contrastive Clustering},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {4315--4327},
doi = {10.1109/tip.2025.3583194}
}
EUVIMED