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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

TinyViT: Fast Pretraining Distillation for Small Vision Transformers


Jul 21, 2022
Kan Wu , Jinnian Zhang , Houwen Peng , Mengchen Liu , Bin Xiao , Jianlong Fu , Lu Yuan

* Accepted by 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

MiniViT: Compressing Vision Transformers with Weight Multiplexing


Apr 14, 2022
Jinnian Zhang , Houwen Peng , Kan Wu , Mengchen Liu , Bin Xiao , Jianlong Fu , Lu Yuan

* Accepted by 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

Searching the Search Space of Vision Transformer


Nov 29, 2021
Minghao Chen , Kan Wu , Bolin Ni , Houwen Peng , Bei Liu , Jianlong Fu , Hongyang Chao , Haibin Ling

* Accepted to NIPS 2021 

   Access Paper or Ask Questions

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

Rethinking and Improving Relative Position Encoding for Vision Transformer


Jul 29, 2021
Kan Wu , Houwen Peng , Minghao Chen , Jianlong Fu , Hongyang Chao

* Accepted by ICCV 2021 

   Access Paper or Ask Questions

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

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search


Apr 29, 2021
Bin Yan , Houwen Peng , Kan Wu , Dong Wang , Jianlong Fu , Huchuan Lu

* Accepted by CVPR 2021, Github: https://github.com/researchmm/LightTrack 

   Access Paper or Ask Questions

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

OAG-BERT: Pre-train Heterogeneous Entity-augmented Academic Language Models


Mar 23, 2021
Xiao Liu , Da Yin , Xingjian Zhang , Kai Su , Kan Wu , Hongxia Yang , Jie Tang


   Access Paper or Ask Questions

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

OAG-BERT: Pre-train Heterogeneous Entity-augmented Academic Language Model


Mar 03, 2021
Xiao Liu , Da Yin , Xingjian Zhang , Kai Su , Kan Wu , Hongxia Yang , Jie Tang


   Access Paper or Ask Questions

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

Harvesting Visual Objects from Internet Images via Deep Learning Based Objectness Assessment


Apr 01, 2019
Kan Wu , Guanbin Li , Haofeng Li , Jianjun Zhang , Yizhou Yu

* Accepted by ACM Transactions on Multimedia Computing, Communications and Applications 

   Access Paper or Ask Questions

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

Weakly Learning to Match Experts in Online Community


May 07, 2018
Yujie Qian , Jie Tang , Kan Wu

* IJCAI 2018 

   Access Paper or Ask Questions

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

Tumour Ellipsification in Ultrasound Images for Treatment Prediction in Breast Cancer


Jan 13, 2017
Mehrdad J. Gangeh , Hamid R. Tizhoosh , Kan Wu , Dun Huang , Hadi Tadayyon , Gregory J. Czarnota

* Accepted at BHI 2017 

   Access Paper or Ask Questions

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