Adding eight register tokens to a CPE-based ViT-B for face recognition yields state-of-the-art verification accuracy on IJB-B and IJB-C while producing smoother attention maps.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
ViT-FREE enables early exiting from pretrained ViTs for face verification with up to 20% speedup and 1.5 accuracy drop on IJB-C, plus a synthetic-data fine-tuning variant for shallow exits.
citing papers explorer
-
Vision Transformers for Face Recognition Need More Registers
Adding eight register tokens to a CPE-based ViT-B for face recognition yields state-of-the-art verification accuracy on IJB-B and IJB-C while producing smoother attention maps.
-
ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation
ViT-FREE enables early exiting from pretrained ViTs for face verification with up to 20% speedup and 1.5 accuracy drop on IJB-C, plus a synthetic-data fine-tuning variant for shallow exits.