Robust incomplete multi-modal clustering with interpolation enhancement and dual-path contrastive optimization

Incomplete multi-modal clustering (IMC) has emerged as a critical challenge in the context of real-world sensing systems, where missing modalities frequently occur due to sensor failure, occlusion, or transmission loss. This paper proposes a novel dual-path clustering framework to address the limitations of existing IMC methods, which either suffer from over-reliance on reconstruction or lack adaptability to varying missing patterns. Specifically, the proposed approach dynamically selects an optimization pathway based on the global missing rate: a contrastive alignment strategy for low missing rates and a gated interpolation-enhanced module for high missing scenarios. To ensure robust representation, the model introduces residual gating to mitigate interpolation noise, and employs dual-level contrastive learning across features and soft cluster assignments to maintain semantic consistency. A self-refining pseudo-label optimization mechanism further guides the training process to convergence. Extensive experiments conducted on three public multi-modal datasets demonstrate that our method achieves competitive or superior clustering performance under various missing rates, while significantly reducing memory consumption and training time compared to state-of-the-art baselines. These findings suggest that the proposed method is well-suited for deployment in edge-intelligent systems and other resource-constrained environments.