Brief

Researchers have developed a new method using register tokens to improve the interpretability and performance of Vision Transformers (ViTs) for face recognition. By adding learnable register tokens to the initial patch embeddings, the ViT-8R model demonstrates more structured and understandable attention maps compared to standard CLS-token or Concatenated Patch Embeddings (CPE) approaches. This enhancement not only mitigates interpretability artifacts but also achieves state-of-the-art results on large-scale benchmarks like IJB-B and IJB-C. AI

Researchers have developed ViT-FREE, a method to make Vision Transformers (ViTs) more efficient for face recognition without retraining. This approach allows for early exiting from intermediate layers of a pre-trained ViT, reducing computational cost while maintaining high accuracy. An additional fine-tuning strategy, ViT-FREE_FT, further optimizes performance for shallower exits by adapting only projection layers with synthetic data. AI