/AW-Net

Primary LanguagePython

AW-Net: Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters

Accepted By TPAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence)

the running environment

python=3.8 
pytorch=1.6
cuda = 11.3
numpy=1.19

training AW-Net on cifar10:

python cifar10_AW_NET_train.py

Citation

@inproceedings{Zhao2024Revisiting,
title={Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters},
author={Xingxing Wei and Shiji Zhao and Bo Li},
booktitle={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2024},
}