A systematic benchmark of 15 vision foundation models for Face Anti-Spoofing reveals that DINOv2 with Registers achieves state-of-the-art cross-domain performance while maintaining computational efficiency.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing
A systematic benchmark of 15 vision foundation models for Face Anti-Spoofing reveals that DINOv2 with Registers achieves state-of-the-art cross-domain performance while maintaining computational efficiency.