HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detection

ArXi:2604.27903v1 Announce Type: new The rapid evolution of generative models has enabled the creation of highly realistic and diverse synthetic images, posing significant challenges to reliable and generalizable Synthetic Image Detection (SID). However, existing detectors are typically trained on limited and biased datasets, resulting in poor generalization to unseen generators. To address this issue, we propose HiMix, a unified framework that enhances generalization by expanding the