用流模型隐空间的拟合度检测异常数据，无需额外训练。
The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
- 利用流模型隐空间的几何性质，通过拟合度判断是否为异常数据。
- 在标准测试中显著优于传统似然方法，且不依赖异常样本。
- 适合对误报率敏感的应用，如医疗诊断和安全系统。
深度生成模型天然适合用于分布外（OOD）检测，但已有研究表明其生成的似然值难以可靠区分分布内与分布外数据。本文利用连续归一化流的微分同胚性和质量保持性，发现分布外样本映射到隐空间后会形成在噪声先验下极不典型的噪声样本，而这种异常无法被似然值捕捉。基于此，我们提出一种新方法——信号在噪声（SITN），可在单样本层面进行分布外检测。SITN 不需要分布外数据，计算开销极小，且能严格控制误报率。在标准基准和合成扰动下的全面评估表明，该方法效果显著，并克服了基于似然方法固有的复杂度偏差。
原文摘要 · Abstract (English)
Deep generative models offer a natural foundation for out-of-distribution (OOD) detection, yet prior work has shown that their assigned likelihoods are notoriously unreliable indicators for in- vs out-of-distribution data. In this paper, we address this problem by leveraging the diffeomorphic and mass-preserving properties of continuous normalising flows. Our analysis shows that OOD samples are mapped to noise samples that are highly atypical under the noise prior in ways not captured by the likelihood. Based on this observation, we propose a new method -- Signal in the Noise (SITN) -- for OOD detection on the single-sample level. SITN requires no access to OOD data, incurs minimal computational overhead, and provides strict control of false positive rates. Comprehensive evaluations through standard benchmarks and synthetic perturbations highlight the method's effectiveness and the absence of the complexity bias inherent to likelihood-based methods.
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。