Sign in
SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning.
Zhenglun Kong
Peiyan Dong
Xiaolong Ma
Xin Meng
Wei Niu
Mengshu Sun
Xuan Shen
Geng Yuan
Bin Ren
Hao Tang
Minghai Qin
Yanzhi Wang
Published in:
ECCV (11) (2022)
Keyphrases
</>
computer vision
vision system
search space
real time
computational vision
memory efficient
pruning algorithm
neural network
artificial intelligence
video sequences
human vision
visual field
pruning method
pruning power
heterogeneous computing