Skip to yearly menu bar Skip to main content


Oral
in
Workshop: Associative Memory & Hopfield Networks in 2023

Hopfield Boosting for Out-of-Distribution Detection

Claus Hofmann · Simon Schmid · Bernhard Lehner · Daniel Klotz · Sepp Hochreiter


Abstract:

Out-of-distribution (OOD) detection is crucial for real-world machine learning. Outlier exposure methods, which use auxiliary outlier data, can significantly enhance OOD detection. We present Hopfield Boosting, a boosting technique employing modern Hopfield energy (MHE) to refine the boundary between in-distribution (ID) and OOD data. Our method focuses on challenging outlier examples near the decision boundary, achieving a 40% improvement in FPR95 on CIFAR-10, setting a new OOD detection state-of-the-art with outlier exposure.

Chat is not available.