Energy-based Hopfield Boosting for Out-of-Distribution Detection
Claus Hofmann, Simon Lucas Schmid, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter
Abstract
Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improve OOD detection performance compared to approaches without advanced training strategies. We introduce Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to focus on hard-to-distinguish auxiliary outlier examples that lie close to the decision boundary between in-distribution and auxiliary outlier data. Our method achieves a new state-of-the-art in OOD detection with outlier exposure, improving the FPR95 from 2.28 to 0.92 on CIFAR-10, from 11.76 to 7.94 on CIFAR-100, and from 50.74 to 36.60 on ImageNet-1K.
BibTeX
@inproceedings{
hofmann2024energybased,
title={Energy-based Hopfield Boosting for Out-of-Distribution Detection},
author={Claus Hofmann and Simon Lucas Schmid and Bernhard Lehner and Daniel Klotz and Sepp Hochreiter},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=VLQYtVMTYz}
}