HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings

TL;DR

HyperMix introduces a hypernetwork-based approach with Mixup and outlier exposure to improve out-of-distribution detection in few-shot learning scenarios, outperforming existing methods on standard benchmarks.

Contribution

The paper proposes HyperMix, a novel hypernetwork framework with Mixup and outlier exposure, specifically designed for few-shot OOD detection, addressing limitations of prior methods.

Findings

HyperMix significantly outperforms existing OOD detection methods in few-shot settings.

The approach does not require additional outlier datasets for out-of-episode exposure.

Experiments on CIFAR-FS and MiniImageNet validate the effectiveness of HyperMix.

Abstract

Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored. Such few-shot OOD settings are challenging, as models have scarce opportunities to learn the data distribution before being tasked with identifying OOD samples. Indeed, we demonstrate that recent state-of-the-art OOD methods fail to outperform simple baselines in the few-shot setting. We thus propose a hypernetwork framework called HyperMix, using Mixup on the generated classifier parameters, as well as a natural out-of-episode outlier exposure technique that does not require an additional outlier dataset. We conduct experiments on CIFAR-FS and MiniImageNet, significantly outperforming other OOD methods in the few-shot regime.