Skip to content

[NeurIPS 2022] FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation

License

Notifications You must be signed in to change notification settings

prs-eth/FILM-Ensemble

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation

Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz, Mina Rezaei, Bernd Bischl, Rodrigo Caye Daudt, Stefano D'Aronco, Jan Dirk Wegner, and Konrad Schindler. - NeurIPS 2022.

[Paper on ArXiv] [Poster]

🌌 Overview

Method overview

✏️ 📄 Citation

If you find our work useful or interesting, please cite our paper:

@inproceedings{turkoglu2022film,
  title={FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation},
  author={Turkoglu, Mehmet Ozgur and Becker, Alexander and G{\"u}nd{\"u}z, H{\"u}seyin Anil and Rezaei, Mina and Bischl, Bernd and Daudt, Rodrigo Caye and D'Aronco, Stefano and Wegner, Jan Dirk and Schindler, Konrad},
  booktitle={Advances in Neural Information Processing Systems},
  year={2022}
}

Reproducing results: Cifar-10 / Cifar-100

Installation

pip install -r requirements.txt

Training

python main.py -e {number of ensemble}