FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection 事件

FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection arXiv:2606.00606v1 Announce Type: new Abstract: Real-world synthetic image detectors often generalize poorly under domain shift despite strong in-domain performance. Using unsupervised UMAP projections, we find that natural and synthetic features remain partially separable on unseen datasets, yet performance still drops, suggesting that the classification head overfits to training-domain artifacts. Therefore, the key