BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse
This addresses the challenge of OOD detection for safety-sensitive applications, but it is incremental as it builds on existing neural collapse concepts and outlier-exposure methods.
The paper tackles the problem of detecting out-of-distribution (OOD) samples in image classifiers, especially when OOD samples are semantically similar to in-distribution classes, by introducing BootOOD, a self-supervised framework that synthesizes pseudo-OOD features and uses a radius-based classification on feature norms, resulting in outperforming prior post-hoc methods and being competitive with state-of-the-art outlier-exposure approaches on datasets like CIFAR-10, CIFAR-100, and ImageNet-200.
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.