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

TL;DR

This paper introduces Hopfield Boosting, a novel method using modern Hopfield energy to improve out-of-distribution detection by focusing on hard-to-distinguish outliers, achieving state-of-the-art results.

Contribution

It presents a new boosting approach that leverages modern Hopfield energy to enhance OOD detection, especially for challenging outliers near the decision boundary.

Findings

Achieves state-of-the-art OOD detection performance.

Significantly reduces FPR95 on CIFAR-10 and CIFAR-100.

Effectively concentrates on hard-to-distinguish outliers.

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 (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.