adaptive model

AViT: Adaptive Tokens for Efficient Vision Transformer

AViT: Adaptive Tokens for Efficient Vision Transformer

Transformer with adaptive inference where simpler images are classified faster. Tokens are automatically stopped at various depth once become irrelevant. Learned via differentiable loss inspired by ACT.

H. Yin, A. Vahdat, J. Alvarez, A. Mallya, J. Kautz, P. Molchanov