FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection
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 is to learn more transferable representations so that the decision criterion is more stable and robust to domain shifts. Based on the structural fact that synthetic images are produced by diverse generators, we propose a hierarchical contrastive learning framework that improves the separability between natural and syntheti...
| Authors | Shan Zhang, Yongxin He, Mingming Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 30 May 2026 |
| Last updated at source | 19 August 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- heyongxin233/FiSeR-DINOv3-ViT-L16Model · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.