用多流形嵌入提升分布外检测，少样本即可达到顶尖效果
Learning Multi-Manifold Embedding for Out-Of-Distribution Detection
- 联合优化球面与双曲空间，构建更丰富的数据表示
- 仅需10个异常样本，即达8000万样本训练的性能
- 无需重训练，适合实际部署中的动态检测场景
在真实应用中，检测分布外（OOD）样本对可信AI至关重要。尽管近年来表示学习和潜在嵌入的发展推动了多种评分算法的进步，但单一嵌入空间难以充分刻画分布内数据并应对多样化的分布外情况。本文提出一种新型多流形嵌入学习（MMEL）框架，联合优化超球面与双曲空间以增强OOD检测能力。该方法生成代表性嵌入，并采用原型感知评分函数区分分布外样本。其仅需极少分布外样本，且无需模型重训练。在六个公开数据集上的实验表明，相比现有基于距离的检测方法，MMEL显著降低了假阳性率（FPR），同时保持高AUC值。我们分析了多流形学习的影响，并可视化各数据集上分布外得分的分布。值得注意的是，仅使用10个分布外样本而无需重训练，其性能即可媲美现代异常暴露方法中使用8000万异常样本训练的结果。
原文摘要 · Abstract (English)
Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the training data. However, a single embedding space falls short in characterizing in-distribution data and defending against diverse OOD conditions. This paper introduces a novel Multi-Manifold Embedding Learning (MMEL) framework, optimizing hypersphere and hyperbolic spaces jointly for enhanced OOD detection. MMEL generates representative embeddings and employs a prototype-aware scoring function to differentiate OOD samples. It operates with very few OOD samples and requires no model retraining. Experiments on six open datasets demonstrate MMEL's significant reduction in FPR while maintaining a high AUC compared to state-of-the-art distance-based OOD detection methods. We analyze the effects of learning multiple manifolds and visualize OOD score distributions across datasets. Notably, enrolling ten OOD samples without retraining achieves comparable FPR and AUC to modern outlier exposure methods using 80 million outlier samples for model training.
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。