Deep Contrastive Multi-view Clustering under Semantic Feature Guidance

arXiv:2403.05768v1 Announce Type: new
Abstract: Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting the performance of existing algorithms from further improvement. To solve this problem, we propose a multi-view clustering framework named Deep Contrastive Multi-view Clustering under Semantic feature guidance (DCMCS) to alleviate the influence of false negative pairs. Specifically, view-specific features are firstly extracted from raw features …

abstract algorithms arxiv clustering construction cs.cv cs.mm false feature guidance however improvement negative performance positive sample semantic solve type view