A-ViT: Adaptive Tokens for Efficient Vision Transformer.

Hongxu Yin Arash Vahdat José M. Álvarez 0004 Arun Mallya Jan Kautz Pavlo Molchanov 0001 A-ViT: Adaptive Tokens for Efficient Vision Transformer. 10799-10808 2022 CVPR https://doi.org/10.1109/CVPR52688.2022.01054 conf/cvpr/2022 db/conf/cvpr/cvpr2022.html#YinVAMKM22