Towards Frequency-Based Explanation for Robust CNN

Oct 28, 2021 1 min read

RobustFreqCNN

About

This repository contains the implementation of the paper “Towards Frequency-Based Explanation for Robust CNN” arxiv. It primarly deals the extent to which image features are robust in the frequency domain.

Steps

It is recommended to setup a fresh virtual environment first.

python -m venv env
source activate env/bin/activate

Install the torchattacks package

pip install torchattacks

Run the main.py file.

The original paper implemented the attacks using a VGG 19 model. However, due to memory constraints I did it using ResNet 18. Here I have provided a fine-tuned version of ResNet 18 which is pre-trained on ImageNet. The checkpoint can be downloaded using this link.

RCT Maps

CW	FGSM	PGD

Disclaimer

This is not an official implementation of the paper. I am not associated with the authors of the paper or Lab in any manner whatsoever and I don’t claim credit for any of the algorithms proposed in the paper.

GitHub

View Github

John was the first writer to have joined pythonawesome.com. He has since then inculcated very effective writing and reviewing culture at pythonawesome which rivals have found impossible to imitate.