厘清分布外检测中语义与协变量的混淆问题，提出可解的新评估框架。
Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection
- 区分语义空间与协变量空间，明确定义分布外样本的可检测性条件。
- 发现现有评估设置下部分分布外样本无法被检测，导致任务不可解。
- 提出可解分布外检测新设定，适用于后验检测方法的理论分析。
分布外（OOD）检测的核心目标是识别具有语义变化的输入，即当训练数据中未包含某类新样本时，应将其判定为分布外而非误分类为已有类别。然而，我们发现当前对“语义变化”的定义模糊，导致某些现有的OOD测试协议对于基于已训练分类器的后验检测方法而言不可解。本文提出了更精确的“语义空间”与“协变量空间”定义，从而理论上分析哪些类型的分布外分布会导致检测任务不可解。为规避现有设置的缺陷，我们进一步定义了“可解分布外”（Tractable OOD）设置，确保后验检测方法能有效区分分布内外样本。最后，通过多个实验验证了定义的必要性与定理的正确性。
原文摘要 · Abstract (English)
The primary goal of out-of-distribution (OOD) detection tasks is to identify inputs with semantic shifts, i.e., if samples from novel classes are absent in the in-distribution (ID) dataset used for training, we should reject these OOD samples rather than misclassifying them into existing ID classes. However, we find the current definition of "semantic shift" is ambiguous, which renders certain OOD testing protocols intractable for the post-hoc OOD detection methods based on a classifier trained on the ID dataset. In this paper, we offer a more precise definition of the Semantic Space and the Covariate Space for the ID distribution, allowing us to theoretically analyze which types of OOD distributions make the detection task intractable. To avoid the flaw in the existing OOD settings, we further define the "Tractable OOD" setting which ensures the distinguishability of OOD and ID distributions for the post-hoc OOD detection methods. Finally, we conduct several experiments to demonstrate the necessity of our definitions and validate the correctness of our theorems.
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。