cvpr2022

Gradvit: Gradient inversion of vision transformers
Gradvit: Gradient inversion of vision transformers
Images can be recovered from averaged gradients in Transformers, they are more vulnerable than CNNs.
Ali Hatamizadeh, Hongxu Yin, Holger Roth, Wenqi Li, Jan Kautz, Daguang Xu, Pavlo Molchanov
PDF Cite Code CVPR2022
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
PDF Cite Code CVPR2022 (Oral)