Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

BiViT: Extremely Compressed Binary Vision Transformer


Nov 14, 2022
Yefei He, Zhenyu Lou, Luoming Zhang, Weijia Wu, Bohan Zhuang, Hong Zhou

Add code

* Under review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

EcoFormer: Energy-Saving Attention with Linear Complexity


Sep 19, 2022
Jing Liu, Zizheng Pan, Haoyu He, Jianfei Cai, Bohan Zhuang

Add code

* Accepted to NeurIPS 2022; First two authors contributed equally 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FocusFormer: Focusing on What We Need via Architecture Sampler


Aug 23, 2022
Jing Liu, Jianfei Cai, Bohan Zhuang

Add code

* Tech report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection


Jul 21, 2022
Yuetian Weng, Zizheng Pan, Mingfei Han, Xiaojun Chang, Bohan Zhuang

Add code

* Accepted to ECCV 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Fast Vision Transformers with HiLo Attention


May 26, 2022
Zizheng Pan, Jianfei Cai, Bohan Zhuang

Add code

* Tech report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Dynamic Focus-aware Positional Queries for Semantic Segmentation


Apr 04, 2022
Haoyu He, Jianfei Cai, Zizheng Pan, Jing Liu, Jing Zhang, Dacheng Tao, Bohan Zhuang

Add code

* Tech report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Automated Progressive Learning for Efficient Training of Vision Transformers


Mar 28, 2022
Changlin Li, Bohan Zhuang, Guangrun Wang, Xiaodan Liang, Xiaojun Chang, Yi Yang

Add code

* Accepted to CVPR 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sharpness-aware Quantization for Deep Neural Networks


Nov 24, 2021
Jing Liu, Jianfei Cai, Bohan Zhuang

Add code

* Tech report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pruning Self-attentions into Convolutional Layers in Single Path


Nov 23, 2021
Haoyu He, Jing Liu, Zizheng Pan, Jianfei Cai, Jing Zhang, Dacheng Tao, Bohan Zhuang

Add code

* Tech report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mesa: A Memory-saving Training Framework for Transformers


Nov 22, 2021
Zizheng Pan, Peng Chen, Haoyu He, Jing Liu, Jianfei Cai, Bohan Zhuang

Add code

* Tech report 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
>>