Skip to content

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)

License

Notifications You must be signed in to change notification settings

visinf/funnybirds

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FunnyBirds

License Framework

R. Hesse, S. Schaub-Meyer, and S. Roth. FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods. ICCV, 2023, oral presentation.

Paper | ArXiv | Video

⚠️ Disclaimer: This repository will contain the full code to reproduce our work, including the dataset rendering, the custom evaluations, and the framework code for all methods (code coming soon). As this code can be a bit unclear, we additionally provide a separat FunnyBirds framework repository that provides the minimal working code to run your own evaluations on the FunnyBirds framework. If you just want to run the framework evaluation, we thus recommend using the FunnyBirds framework repository.

News:

  • The FunnyBirds framework repository is ready to evaluate your own methods (September 13, 2023)
  • You can now render the dataset yourself (October 23, 2023)
  • We have added the code for the custom evaluations (February 14, 2024)

Getting Started

The following section provides a very detailed description of how to use the FunnyBirds framework. Even if the instructions might seem a bit long and intimidating, most of the steps are finished very quickly. So don't lose hope and if you have recommendations on how to improve the framework or the instructions, we would be grateful for your feedback.

Download the dataset

The dataset requires ~1.6GB free disk space.

cd /path/to/dataset/
wget download.visinf.tu-darmstadt.de/data/funnybirds/FunnyBirds.zip
unzip FunnyBirds.zip
rm FunnyBirds.zip

Set up the environment

If you use conda you can create your environment as shown below:

conda create --name funnybirds-framework python=3.7
conda activate funnybirds-framework
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
conda install captum -c pytorch
conda install -c conda-forge tqdm
conda install -c anaconda scipy
conda install -c conda-forge nodejs
pip install opencv-contrib-python (conda install -c conda-forge opencv messes the environment up) 

Dataset Generation

To render the FunnyBirds dataset, please refer to the render folder.

Custom Evaluations

To run the custom evaluations, please refer to the custom_evaluation folder.

About

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published