FDGC: Fuzzy deep clustering with dual-granularity contrastive learning

Deep clustering has garnered considerable attention in data mining and computer vision due to its effectiveness in handling high-dimensional data. However, traditional deep clustering methods face notable limitations. Real-world data often exhibit complex feature distributions and ambiguous boundaries. Fixed network architectures struggle to capture both global and local dependencies among data samples and are inadequate for managing fuzzy boundaries. Additionally, contrastive learning methods commonly used in deep clustering suffer from inefficient negative sample selection, where many positive samples are mistakenly treated as negative, thereby hindering training. To address these challenges, this paper proposes a fuzzy deep clustering method with dual-granularity contrastive learning (FDGC). The method extracts features and clusters them to generate pseudo-labels, retaining only the reliable ones through a confidence screening mechanism for use as supervision signals. By integrating data augmentation strategies with a self-attention fuzzy network, FDGC effectively captures both context and local details while dynamically adapting to feature fuzziness. Furthermore, a dual-granularity contrastive loss function is introduced to enhance feature representation. This loss improves sample discriminability at both the cluster and instance levels, significantly mitigating the issue of inaccurate negative sampling in traditional contrastive learning. Experimental results across multiple benchmark datasets demonstrate that FDGC outperforms existing method, validating the effectiveness of the proposed approach.