Jul 2026
DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing
The results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.
Pierre Gallin-Martel, Mika Feng, Koichi Ito et al.
· arXiv.org · 0 citations