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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Structural Pruning via Latency-Saliency Knapsack


Oct 18, 2022
Maying Shen, Hongxu Yin, Pavlo Molchanov, Lei Mao, Jianna Liu, Jose M. Alvarez

Add code

* Accepted by NeurIPS 2022. arXiv admin note: substantial text overlap with arXiv:2110.10811 

   Access Paper or Ask Questions

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

Global Context Vision Transformers


Jun 20, 2022
Ali Hatamizadeh, Hongxu Yin, Jan Kautz, Pavlo Molchanov

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

GradViT: Gradient Inversion of Vision Transformers


Mar 28, 2022
Ali Hatamizadeh, Hongxu Yin, Holger Roth, Wenqi Li, Jan Kautz, Daguang Xu, Pavlo Molchanov

Add code

* CVPR'22 Accepted Paper 

   Access Paper or Ask Questions

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

Do Gradient Inversion Attacks Make Federated Learning Unsafe?


Feb 14, 2022
Ali Hatamizadeh, Hongxu Yin, Pavlo Molchanov, Andriy Myronenko, Wenqi Li, Prerna Dogra, Andrew Feng, Mona G. Flores, Jan Kautz, Daguang Xu, Holger R. Roth

Add code

* Improved and reformatted version of https://www.researchsquare.com/article/rs-1147182/v2 

   Access Paper or Ask Questions

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

AdaViT: Adaptive Tokens for Efficient Vision Transformer


Dec 14, 2021
Hongxu Yin, Arash Vahdat, Jose Alvarez, Arun Mallya, Jan Kautz, Pavlo Molchanov

Add code


   Access Paper or Ask Questions

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

When to Prune? A Policy towards Early Structural Pruning


Oct 22, 2021
Maying Shen, Pavlo Molchanov, Hongxu Yin, Jose M. Alvarez

Add code


   Access Paper or Ask Questions

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

HALP: Hardware-Aware Latency Pruning


Oct 20, 2021
Maying Shen, Hongxu Yin, Pavlo Molchanov, Lei Mao, Jianna Liu, Jose M. Alvarez

Add code


   Access Paper or Ask Questions

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

NViT: Vision Transformer Compression and Parameter Redistribution


Oct 10, 2021
Huanrui Yang, Hongxu Yin, Pavlo Molchanov, Hai Li, Jan Kautz

Add code


   Access Paper or Ask Questions

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

Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion


Jul 13, 2021
Xin Dong, Hongxu Yin, Jose M. Alvarez, Jan Kautz, Pavlo Molchanov

Add code

* A new inversion method to reverse neural networks and get input from intermediate feature maps. Works without original data for classifiers and GANs 

   Access Paper or Ask Questions

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

HANT: Hardware-Aware Network Transformation


Jul 12, 2021
Pavlo Molchanov, Jimmy Hall, Hongxu Yin, Jan Kautz, Nicolo Fusi, Arash Vahdat

Add code


   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
>>