Skip to content
/ PAR Public

Implementation of Patch-wise Adversarial Regularization from "Learning Robust Global Representations by Penalizing Local Predictive Power"

Notifications You must be signed in to change notification settings

HaohanWang/PAR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Patch-wise Adversarial Regularization

PAR

Example Usage of the Regularization

  • example/AlexNet.py
    • Example usuage of how to plug in our idea into existing AlexNet
    • One only need to concern with the codes controlled by the boolean varialable adv_flag, including:
  • utility/
    • Other codes needed to run the AlexNet, not part of the contributions of this repository

Replication

  • This repository is made for a clear demonstration of our method. For replication of the numbers in our paper, please visit: HaohanWang/PAR_experiments

Data

Reference

If you find this method helpful, please consider cite:

Haohan Wang, Songwei Ge, Eric P. Xing, and Zachary C. Lipton. "Learning Robust Global Representations by Penalizing Local Predictive Power" (NeurIPS 2019)

Other Resources

About

Implementation of Patch-wise Adversarial Regularization from "Learning Robust Global Representations by Penalizing Local Predictive Power"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages