ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation
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
IMPACT Enables more efficient deployment of powerful Vision Transformer models on resource-constrained devices for face recognition tasks.