This is a fork of official repository of ColorFool: Semantic Adversarial Colorization, a work published in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, Washington, USA, 14-19 June, 2020.
Example of results
| Original Image | Attack AlexNet | Attack ResNet18 | Attack ResNet50 |
|---|---|---|---|
 |
 |
 |
 |
This fork is aimed to simplify integration of the model into REST API.
- Download source code from GitHub
git clone https://github.com/vBazilevich/ColorFool.git - Create conda virtual-environment
conda create --name ColorFool python=3.5.6 - Activate conda environment
source activate ColorFool - Install requirements
pip install -r requirements.txt
Note: you can get rid of conda but be ready to handle dependencies manually.
Just pass a binary array to colorize function from ColorFool module.
Note: to make it working you must download segmentation model (both encoder and decoder) from here and locate in "Segmentation/models" directory.
Function colorize returns a binary array that encodes produced colorful image.
@InProceedings{shamsabadi2020colorfool,
title = {ColorFool: Semantic Adversarial Colorization},
author = {Shamsabadi, Ali Shahin and Sanchez-Matilla, Ricardo and Cavallaro, Andrea},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2020},
address = {Seattle, Washington, USA},
month = June
}
This work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.