Exploring the link between uncertainty estimates obtained by "exact" Bayesian inference and out-of-distribution (OOD) detection. Here, you can find a talk motivating the project.
The code in this repository requires the installation of the hypnettorch package.
The subfolder notebooks jupyter notebook to reproduce experiments from our papers, but they also show how to use the code in this repo. Further usage examples can be found in the subfolder tutorials.
The folder nngp contains utilities to work with NNGP kernels.
Documentation can be found in folder docs. Using sphinx, the documentation can be compiled within this folder by executing make html
. The compiled documentation can be opened via the file index.html.
When using this package in your research project, please consider citing one of our papers for which this package has been developed.
@misc{dangelo:henning:2022:uncertainty:based:ood,
title={On out-of-distribution detection with Bayesian neural networks},
author={Francesco D'Angelo and Christian Henning},
year={2021},
eprint={2110.06020},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@inproceedings{henning:dangelo:2021:bayesian:ood,
title={Are Bayesian neural networks intrinsically good at out-of-distribution detection?},
author={Christian Henning and Francesco D'Angelo and Benjamin F. Grewe},
booktitle={ICML Workshop on Uncertainty and Robustness in Deep Learning},
year={2021},
url={https://arxiv.org/abs/2107.12248}
}