Preprint
Aug 2026
PatchHead: Learning Spatial Patch Evidence for Generalizable AI-Generated Image Detection
Qualitative analysis suggests that PatchHead reduces class-conditional domain discrepancy, and redirects the representation from content-dominated saliency toward spatially distributed authenticity evidence, which provides a representation-level account of why spatial patch aggregation transfers more reliably across generators and datasets than a single CLS-based global representation.
Shengbo Qi, Hongyi Fang, Benjia Zhou et al.
· 0 citations