VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection

TL;DR

This paper introduces a data-free method for long-tailed out-of-distribution detection that synthesizes virtual outliers using a geometry-guided approach, eliminating the need for external datasets while achieving superior performance.

Contribution

The authors propose a novel geometry-guided virtual outlier synthesis (GOS) strategy and a dual-granularity semantic loss (DGS) for effective OOD detection without external data.

Findings

Outperforms state-of-the-art methods on CIFAR-LT benchmarks.

Effectively synthesizes outliers using vMF distribution on a hypersphere.

Eliminates reliance on external datasets while maintaining high detection accuracy.

Abstract

Out-of-Distribution (OOD) detection under long-tailed distributions is a highly challenging task because the scarcity of samples in tail classes leads to blurred decision boundaries in the feature space. Current state-of-the-art (sota) methods typically employ Outlier Exposure (OE) strategies, relying on large-scale real external datasets (such as 80 Million Tiny Images) to regularize the feature space. However, this dependence on external data often becomes infeasible in practical deployment due to high data acquisition costs and privacy sensitivity. To this end, we propose a novel data-free framework aimed at completely eliminating reliance on external datasets while maintaining superior detection performance. We introduce a Geometry-guided virtual Outlier Synthesis (GOS) strategy that models statistical properties using the von Mises-Fisher (vMF) distribution on a hypersphere. Specifically, we locate a low-likelihood annulus in the feature space and perform directional sampling of virtual outliers in this region. Simultaneously, we introduce a new Dual-Granularity Semantic Loss (DGS) that utilizes contrastive learning to maximize the distinction between in-distribution (ID) features and these synthesized boundary outliers. Extensive experiments on benchmarks such as CIFAR-LT demonstrate that our method outperforms sota approaches that utilize external real images.