PMCF: A Progressive Multi-Level Collaborative Framework for Face Forgery Detection
The rapid advancement of deepfake image generation poses significant threats to information security and social trust, with forgery artifacts exhibiting multi-scale characteristics from micro-level noise to macro-level semantic anomalies.Existing detection methods are limited by single-scale feature extraction and inefficient fusion due to semantic gaps between deep and shallow features.To address these issues, this letter proposes a Progressive Multi-Level Collaborative Framework (PMCF) comprising a multi-granularity collaborative attention (MGCA) module and a multi-level attention fusion (MLAF) module. MGCA uses three parallel Transformer branches to model pixel-level textures, local structures, and global semantics, while MLAF integrates a feature pyramid, joint attention, and progressive bidirectional fusion for effective feature alignment. Experimental results show consistent AUC improvements over comparative methods across multiple datasets.