Login / Signup
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference.
Haoran You
Yunyang Xiong
Xiaoliang Dai
Bichen Wu
Peizhao Zhang
Haoqi Fan
Peter Vajda
Yingyan Lin
Published in:
CoRR (2022)
Keyphrases
</>
computer vision
neural network
bayesian networks
vision system
real time
genetic algorithm
artificial intelligence
visual attention
information systems
image processing
website