Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection.pdf. Github.

Jiazhen Yan, Ziqiang Li, Fan Wang, Ziwen He, Zhangjie Fu.

• We utilize a sliding window to restrict the attention mechanism to a local window, and reconstruct the features within the window to model the relationships between neighboring internal elements within the local region.

DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection.pdf. Github.

Jiazhen Yan, Ziqiang Li, Fan Wang, Boyu Wang, Ziwen He, Zhangjie Fu.

• We introduce a novel gradient-space decomposition that disentangles CLIP representations into transferable pre-trained priors and task-irrelevant components.

NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection.pdf. Github.

Jiazhen Yan*, Fan Wang*, Ziwen He, Ziqiang Li, Zhangjie Fu.

• we propose a novel detection framework that leverages NULL-Space projection to decouple semantic information from CLIP’s visual features, followed by contrastive learning to capture intrinsic distributional differences between real and generated images.