VMF-GOS：基于几何的虚拟异常合成用于长尾OOD检测
VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
AI总结：
VMF-GOS通过几何引导的虚拟异常合成方法，在无需外部数据的情况下提升长尾分布下OOD检测的性能。
摘要：
在长尾分布下进行Out-of-Distribution（OOD）检测是一项极具挑战性的任务，因为尾部类别的样本稀缺导致特征空间中的决策边界模糊。当前最先进的（sota）方法通常采用异常暴露（OE）策略，依赖大规模真实外部数据集（如8000万张Tiny Images）来正则化特征空间。然而，这种对外部数据的依赖在实际部署中往往由于高数据获取成本和隐私敏感性而变得不可行。为此，我们提出了一种全新的无数据框架，旨在完全消除对外部数据集的依赖，同时保持优越的检测性能。我们引入了一种基于几何的虚拟异常合成（GOS）策略，利用von Mises-Fisher（vMF）分布在超球面上建模统计特性。具体来说，我们定位特征空间中的低概率环形区域，并在此区域内进行方向采样生成虚拟异常。同时，我们引入了一种新的双粒度语义损失（DGS），利用对比学习最大化分布内（ID）特征与这些合成边界异常之间的区别。在CIFAR-LT等基准测试中，我们的方法在使用真实图像的sota方法上表现更优。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
