Deep Clustering via Gradual Community Detection
This work addresses deep clustering for AI applications by introducing a novel network analysis perspective, though it appears incremental as it builds on existing backbones.
The paper tackles the challenge of inadequate supervision signals in deep clustering by proposing a gradual community detection strategy that initializes many pseudo-communities and merges them, leveraging global structural characteristics to enhance pseudo-label purity. Experiments on benchmark image datasets show it effectively improves state-of-the-art performance.
Deep clustering is an essential task in modern artificial intelligence, aiming to partition a set of data samples into a given number of homogeneous groups (i.e., clusters). Recent studies have proposed increasingly advanced deep neural networks and training strategies for deep clustering, effectively improving performance. However, deep clustering generally remains challenging due to the inadequacy of supervision signals. Building upon the existing representation learning backbones, this paper proposes a novel clustering strategy of gradual community detection. It initializes clustering by partitioning samples into many pseudo-communities and then gradually expands clusters by community merging. Compared with the existing clustering strategies, community detection factors in the new perspective of cluster network analysis in the clustering process. The new perspective can effectively leverage global structural characteristics to enhance cluster pseudo-label purity, which is critical to the performance of self-supervision. We have implemented the proposed approach based on the popular backbones and evaluated its efficacy on benchmark image datasets. Our extensive experiments have shown that the proposed clustering strategy can effectively improve the SOTA performance. Our ablation study also demonstrates that the new network perspective can effectively improve community pseudo-label purity, resulting in improved self-supervision.