Robust Prototype Completion for Incomplete Multi-view Clustering
Abstract: In practical data collection processes, certain views may become partially unavailable due to sensor failures or equipment issues, leading to the problem of incomplete multi-view clustering (IMVC). While some IMVC methods employing prototype completion achieve satisfactory performance, almost all of them implicitly assume correct alignment of prototypes across all views. However, during prototype generation, different networks could generate different cluster centers, thereby leading to the produced prototypes from different views may be misaligned, i.e., prototype noisy correspondence. To address this issue, we propose Robust Prototype Completion for Incomplete Multi-view Clustering (RPCIC), which mitigates the impact of noisy correspondence in prototypes. Specifically, RPCIC initially utilizes cross-view contrastive learning module to obtain consistent feature representations across different views. Subsequently, we devise robust contrastive loss for the produced prototypes, aiming to alleviate the influence of noisy correspondence within them. Finally, we employ prototype fusion-based strategy to complete the missing data. Comprehensive experiments demonstrate that RPCIC outperforms 11 state-of-the-art methods in terms of both performance and robustness.
Primary Subject Area: [Experience] Multimedia Applications
Secondary Subject Area: [Content] Multimodal Fusion
Relevance To Conference: Robust prototype completion for incomplete multi-view clustering is a significant contribution to multimedia/multimodal processing because it addresses challenges related to handling incomplete and heterogeneous multi-view data. In addition, in many multimedia processing tasks, feature representation plays a crucial role. Robust prototype completion techniques contribute to improving feature representation by effectively handling missing or incomplete features. By robust prototype completion, these methods can help in achieving more robust and informative feature representations, which in turn leads to better performance in tasks.
Submission Number: 3748
Loading