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

arXiv: https://arxiv.org/abs/2602.05415 · HTML: https://mlsanity.com/paper/2602.05415/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [Non-Parametric Outlier Synthesis](https://mlsanity.com/paper/2303.02966/) (2023)
- [Semantically Coherent Out-of-Distribution Detection](https://mlsanity.com/paper/2108.11941/) (2021)
- [Implicit Semantic Data Augmentation for Deep Networks](https://mlsanity.com/paper/1909.12220/) (2019)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Exploring Classification Equilibrium in Long-Tailed Object Detection](https://mlsanity.com/paper/2108.07507/) (2021)
- [Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition](https://mlsanity.com/paper/2207.01160/) (2022)
- [Probabilistic Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2403.06726/) (2024)
- [Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation](https://mlsanity.com/paper/2310.13923/) (2023)
- [How Re-sampling Helps for Long-Tail Learning?](https://mlsanity.com/paper/2310.18236/) (2023)
- [Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification](https://mlsanity.com/paper/2112.07928/) (2021)
- [Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning](https://mlsanity.com/paper/2312.10686/) (2023)
- [EAT: Towards Long-Tailed Out-of-Distribution Detection](https://mlsanity.com/paper/2312.08939/) (2023)
- [Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail](https://mlsanity.com/paper/2408.06742/) (2024)
- [A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection](https://mlsanity.com/paper/2510.13093/) (2025)

## Built on by (most cited first, 1 of 1)

- [Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?](https://mlsanity.com/paper/2609.38784/) (2026)

## Abstract (arXiv)

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.