Home
News
Members
Publications
NVIDIA Research
Light
Dark
Automatic
FasterViT: Fast Vision Transformers with Hierarchical Attention
Ali Hatamizadeh
,
Greg Heinrich
,
Hongxu (Danny) Yin
,
Andrew Tao
,
Jose M. Alvarez
,
Jan Kautz
,
Pavlo Molchanov
May 2024
Cite
arXiv
Website
Type
Conference paper
Publication
International Conference on Learning Representations (ICLR)
Ali Hatamizadeh
Greg Heinrich
Hongxu (Danny) Yin
Jan Kautz
Team Leader
Pavlo Molchanov
Related
Global Context Vision Transformers
A-ViT: Adaptive Tokens for Efficient Vision Transformer
Do Gradient Inversion Attacks Make Federated Learning Unsafe?
Flextron: Many-in-One Flexible Large Language Model
GradViT: Gradient Inversion of Vision Transformers
Cite
×