Enhanced multi-view image clustering via dual-fusion contrastive learning
TL;DR
DFCMVC is proposed, a dual-fusion framework featuring a differentiable, attention-based encoder (SBMHE) that implicitly learns view-specific architectural weights via dynamic gating, enabling end-to-end adaptation of representational capacity.
Abstract
Multi-view clustering (MVC) in the foundation model era demands architectures that jointly optimize representation power, efficiency, and deployability–core goals of neural architecture search (NAS). Existing deep MVC methods rely on fixed fusion designs, lacking adaptability to heterogeneous views and structural co-optimization with clustering objectives. We propose DFCMVC, a dual-fusion framework featuring a differentiable, attention-based encoder (SBMHE) that implicitly learns view-specific architectural weights via dynamic gating, enabling end-to-end adaptation of representational capacity. This design embodies a NAS-amenable paradigm: its modular, multi-head structure naturally supports searchable fusion topologies and view selection under multi-objective constraints (e.g., accuracy, latency). By aligning deep contrastive learning with interpretable subspace clustering through Jensen-Shannon divergence, DFCMVC ensures both performance and transparency–critical for real-world deployment in multimodal systems. Experiments on seven benchmarks show state-of-the-art results, demonstrating its promise as a scalable, automated foundation for multi-view model design. Code: https://github.com/lab-807/DFCMVC.