AI RESEARCH

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

arXiv CS.CV

ArXi:2606.00606v1 Announce Type: new 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