用潜在空间扩散模型提升异常检测准确率
Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
- 在预训练ResNet-18的特征空间训练变分扩散模型
- 在OpenOOD基准上优于现有主流方法
- 证明潜在空间更利于密度估计与异常检测
尽管人工智能发展迅速，安全仍是部署机器学习系统的主要瓶颈。关键安全环节是分布外（OOD）检测：给定输入，判断其是否来自训练数据分布。生成模型中最自然的OOD评分指标是数据似然。本文证明，在均匀分布的OOD数据假设下，似然正是最优的OOD检测器。然而，早期研究发现似然在实践中常失效，引发对其有效性的质疑。我们探究问题根源：是表示空间难以学习良好的密度估计，还是仅因生成模型通常使用像素空间所致？为此，我们在预训练ResNet-18的表示空间而非图像空间上训练变分扩散模型，评估基于似然的检测器在与OpenOOD套件中最新方法对比下的表现。
原文摘要 · Abstract (English)
Despite rapid advances in AI, safety remains the main bottleneck to deploying machine-learning systems. A critical safety component is out-of-distribution detection: given an input, decide whether it comes from the same distribution as the training data. In generative models, the most natural OOD score is the data likelihood. Actually, under the assumption of uniformly distributed OOD data, the likelihood is even the optimal OOD detector, as we show in this work. However, earlier work reported that likelihood often fails in practice, raising doubts about its usefulness. We explore whether, in practice, the representation space also suffers from the inability to learn good density estimation for OOD detection, or if it is merely a problem of the pixel space typically used in generative models. To test this, we trained a Variational Diffusion Model not on images, but on the representation space of a pre-trained ResNet-18 to assess the performance of our likelihood-based detector in comparison to state-of-the-art methods from the OpenOOD suite.
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。