NeurIPS’21: Probabilistic Margins for Instance Reweighting in Adversarial Training (Pytorch implementation)

NeurIPS’21: Probabilistic Margins for Instance Reweighting in Adversarial Training (Pytorch implementation).

This is the code for the paper:

Probabilistic Margins for Instance Reweighting in Adversarial Training

Qizhou Wang*, Feng Liu*, Bo Han, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, Masashi Sugiyama

To be presented at NeurIPS 2021.

If you find this code useful in your research then please cite:

@inproceedings{wang2021probabilistic,
title={Probabilistic Margins for Instance Reweighting in Adversarial Training,
author={Qizhou Wang and Feng Liu and Bo Han and Tongliang Liu and Chen Gong and Gang Niu and Mingyuan Zhou and Masashi Sugiyama},
booktitle={NeurIPS},
year={2021}
}

Setups

All code was developed and tested on a single machine equipped with an NVIDIA GTX3090 GPU.

The environment is as bellow:

  • Ubuntu 18.04
  • CUDA 10.2.89
  • Python 3.7.6 (Anaconda 4.9.2 64 bit)
  • PyTorch 1.5.0
  • numpy 1.18.1

Usage

python main.py

Source: https://github.com/QizhouWang/MAIL?ref=pythonawesome.com

Default image
Lingaraj Senapati
Hey There! I am Lingaraj Senapati, the Co-founder of lingarajtechhub.com My skills are Freelance, Web Developer & Designer, Corporate Trainer, Digital Marketer & Youtuber.
Articles: 253

Newsletter Updates

Enter your email address below to subscribe to our newsletter