Soft Neighbors Supported Contrastive Clustering

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 inadequately models inter-sample relationships, leading to class collision and degraded clustering performance. In this paper, we propose a soft neighbor supported contrastive clustering method to address this issue. Specifically, we propose the perception radius concept to quantify similarity confidence between a sample and its neighbors. Building 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 introduce 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.