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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers


Mar 27, 2022
Yunjie Tian, Lingxi Xie, Jiemin Fang, Mengnan Shi, Junran Peng, Xiaopeng Zhang, Jianbin Jiao, Qi Tian, Qixiang Ye

* 20 pages, 5 figures, 3 tables 

   Access Paper or Ask Questions

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

Feature-Gate Coupling for Dynamic Network Pruning


Nov 29, 2021
Mengnan Shi, Chang Liu, Qixiang Ye, Jianbin Jiao

* 31 pages 

   Access Paper or Ask Questions

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

A scalable convolutional neural network for task-specified scenarios via knowledge distillation


Jan 06, 2017
Mengnan Shi, Fei Qin, Qixiang Ye, Zhenjun Han, Jianbin Jiao


   Access Paper or Ask Questions

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