Hua-Zhu Chen

End-to-end sample-quality-adaptive contrastive fusion for deep multi-view clustering

An End-to-end Sample-Quality-Adaptive Contrastive Fusion for Deep Multi-View Clustering (SACC) framework, which dynamically adjusts the contrastive learning intensity according to sample-wise cross-view inconsistency calculated via squared Euclidean distance discrepancy and cosine similarity difference is proposed.