不靠复杂训练,用几何优化让旧模型也能精准识别罕见异常数据。
Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry

- 将特征归一化到单位球面,用全局协方差替代类别专属协方差。
- 在CIFAR-LT上将检测性能从46.49提升至85.67(AUROC)。
- 无需额外训练,适合想快速提升现有模型异常检测能力的研究者。
长尾分布外样本(LT-OOD)检测通常依赖专用训练策略,如辅助异常数据、弃权头、对比损失、能量损失或梯度冲突控制。本文指出,这些机制可能掩盖了一个更简单的事实:冻结的长尾表示本身已蕴含有用异常信号,但原始马氏距离受频率耦合的特征半径和尾部协方差不足影响而失真。为此提出超球面池化马氏(HPM)检测器,将特征归一化至单位球面,用池化且岭正则化的度量替代类别特定协方差,同时保留类别均值作为语义锚点。在CIFAR-LT实验及ImageNet-100-LT近域边界分析中,HPM显著优于原始马氏评分;对于先验校准的普通训练(PC-ERM),其在CIFAR-10-LT上将AUROC从46.49提升至85.67,在CIFAR-100-LT上从50.40提升至78.35。该简单流水线还取得最佳日志效率得分(LES: 3.08),在显著降低训练成本的同时保持约95%的最优检测性能。结果表明应将表征质量、检测器几何与训练复杂度分开评估。
原文摘要 · Abstract (English)
Long-tailed out-of-distribution (LT-OOD) detection is often addressed with specialized training, including auxiliary out-of-distribution (OOD) data, abstention heads, contrastive objectives, energy losses, or gradient-conflict control. We show that these training mechanisms can obscure a simpler issue: frozen long-tailed representations may already contain useful OOD evidence, but raw Mahalanobis distance is distorted by frequency-coupled feature radius and poorly supported tail covariance. We propose Hyperspherical Pooled Mahalanobis (HPM), a post-hoc detector that normalizes features onto the unit sphere and replaces class-specific covariance with a pooled, ridge-regularized metric while keeping class means as semantic anchors. In CIFAR-LT experiments and an ImageNet-100-LT near-OOD boundary analysis, HPM improves raw Mahalanobis scoring; for Prior-Calibrated ERM (PC-ERM), it raises AUROC from 46.49 to 85.67 on CIFAR-10-LT and from 50.40 to 78.35 on CIFAR-100-LT. This simple PC-ERM+HPM pipeline also achieves the best Log Efficiency Score (LES; 3.08) on CIFAR-100-LT, retaining roughly 95% of the best CIFAR-100-LT AUROC observed among the compared post-hoc scores at substantially lower training-time cost. These results argue for evaluating representation quality, detector geometry, and training complexity as separate factors in LT-OOD detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。