SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning
Zhenglun Kong(Harvard University), Yanzhi Wang(Sichuan University), Wei Niu(William & Mary), Hao Tang(Texas State University), Bin Ren(William & Mary), Xiaolong Ma(Ningxia University), Mengshu Sun(Boston University), Minghai Qin(Northeastern University), Peiyan Dong(IIT@MIT), Geng Yuan(Northeastern University), Xuan Shen(Northeastern University), Xin Meng(Peking University)
Cited by 143
Related Papers
Incidence, Clinical Course, and Predictors of Prolonged Recovery Time Following Sport-Related Concussion in High School and College Athletes
|Journal of the International Neuropsychological Society|2012|501
A Systematic DNN Weight Pruning Framework Using Alternating Direction Method of Multipliers
|Lecture notes in computer science|2018|498
Deep Reinforcement Learning for Building HVAC Control
|Unknown|2017|447
Adversarial T-Shirt! Evading Person Detectors in a Physical World
|Lecture notes in computer science|2020|296