用扩散模型先验检测图像分布偏移，可定位异常区域且无需额外数据。
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
- 基于扩散先验与后验的KL散度，无需校准数据即可检测分布偏移。
- 能识别整体异常和局部异常，如健康肝部与肿瘤CT的细微差异。
- 适用于多种扩散模型、数据集和逆问题，适合医学影像异常检测。
扩散模型作为计算成像中的数据驱动先验表现出色，并具备一定的分布外（OOD）图像检测能力。然而，现有方法通常需要了解偏移分布、难以发现微小或局部分布偏移，且仅在完整图像上操作，无法处理逆问题中的间接测量。本文提出一种基于扩散先验与后验分布间KL散度的OOD检测指标，无需任何校准数据或对偏移分布的先验知识，可同时检测整图及图像内部的局部异常区域。实验表明，该指标能有效识别如健康肝部CT与含肿瘤图像间的细微但语义有意义的分布偏移，并在不同扩散模型、数据集和逆问题间具有良好泛化性。代码已开源：https://github.com/voilalab/KLIP。
原文摘要 · Abstract (English)
Diffusion models have shown promising performance as data-driven priors for computational imaging, as well as some capacity to detect out-of-distribution (OOD) images. However, existing approaches to OOD detection often require some knowledge of the shifted distribution, fail to detect subtle or localized distribution shifts, and operate on full images, rather than the indirect measurements available in inverse problems. We propose an OOD detection metric based on the Kullback-Leibler divergence between the diffusion prior and the posterior distribution, that (i) does not require any calibration data or knowledge of the shifted distribution, and (ii) can detect whole images as OOD as well as localize OOD patches within an image. Experimentally, we show that this metric can detect subtle yet semantically meaningful distribution shifts, such as the shift from healthy liver CT scans to those with tumors, and generalizes across different types of diffusion models, datasets, and inverse problems. Our code can be found at https://github.com/voilalab/KLIP.
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。