BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse

TL;DR

BootOOD introduces a self-supervised framework for out-of-distribution detection that synthesizes pseudo-OOD features and leverages Neural Collapse, effectively handling semantically similar OOD samples without requiring outlier exposure.

Contribution

It proposes a novel self-supervised method that uses feature transformations and a radius-based classifier to improve OOD detection under Neural Collapse.

Findings

Outperforms prior post-hoc OOD detection methods.

Surpasses training-based methods without outlier exposure.

Competitive with state-of-the-art outlier-exposure approaches.

Abstract

Out-of-distribution (OOD) detection is critical for deploying image classifiers in safety-sensitive environments, yet existing detectors often struggle when OOD samples are semantically similar to the in-distribution (ID) classes. We present BootOOD, a fully self-supervised OOD detection framework that bootstraps exclusively from ID data and is explicitly designed to handle semantically challenging OOD samples. BootOOD synthesizes pseudo-OOD features through simple transformations of ID representations and leverages Neural Collapse (NC), where ID features cluster tightly around class means with consistent feature norms. Unlike prior approaches that aim to constrain OOD features into subspaces orthogonal to the collapsed ID means, BootOOD introduces a lightweight auxiliary head that performs radius-based classification on feature norms. This design decouples OOD detection from the primary classifier and imposes a relaxed requirement: OOD samples are learned to have smaller feature norms than ID features, which is easier to satisfy when ID and OOD are semantically close. Experiments on CIFAR-10, CIFAR-100, and ImageNet-200 show that BootOOD outperforms prior post-hoc methods, surpasses training-based methods without outlier exposure, and is competitive with state-of-the-art outlier-exposure approaches while maintaining or improving ID accuracy.