Energy-based Hopfield Boosting for Out-of-Distribution Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hofmann, Claus, Schmid, Simon, Lehner, Bernhard, Klotz, Daniel, Hochreiter, Sepp
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916556615712768
author Hofmann, Claus
Schmid, Simon
Lehner, Bernhard
Klotz, Daniel
Hochreiter, Sepp
author_facet Hofmann, Claus
Schmid, Simon
Lehner, Bernhard
Klotz, Daniel
Hochreiter, Sepp
contents 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 (MHE) to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to concentrate 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 metric from 2.28 to 0.92 on CIFAR-10 and from 11.76 to 7.94 on CIFAR-100.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08766
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Energy-based Hopfield Boosting for Out-of-Distribution Detection
Hofmann, Claus
Schmid, Simon
Lehner, Bernhard
Klotz, Daniel
Hochreiter, Sepp
Machine Learning
Computer Vision and Pattern Recognition
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 (MHE) to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to concentrate 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 metric from 2.28 to 0.92 on CIFAR-10 and from 11.76 to 7.94 on CIFAR-100.
title Energy-based Hopfield Boosting for Out-of-Distribution Detection
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.08766