Home
News
Members
Publications
NVIDIA Research
Light
Dark
Automatic
A-ViT: Adaptive Tokens for Efficient Vision Transformer
Hongxu (Danny) Yin
,
Arash Vahdat
,
Jose M. Alvarez
,
Arun Mallya
,
Jan Kautz
,
Pavlo Molchanov
June 2022
Cite
arXiv
Website
Type
Conference paper
Publication
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hongxu (Danny) Yin
Arash Vahdat
Jan Kautz
Team Leader
Pavlo Molchanov
Related
See through Gradients: Image Batch Recovery via GradInversion
FasterViT: Fast Vision Transformers with Hierarchical Attention
LANA: Latency Aware Network Acceleration
Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models
Cite
×