Georgia Institute of Technology
KLIP: Localized distribution shift detection via KL-divergence with diffusion priors in inverse problems
Abstract
dc:description.abstractDiffusion 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
Degree
thesis:*- Name thesis:degree_name
- Electrical and Computer Engineering, MS
- Department thesis:degree_department
- Electrical and Computer Engineering
- Grantor
- Georgia Institute of Technology
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kheirandish, Alireza
- Advisors dc:contributor.advisor
-
- Fridovich-Keil, Sara
- Aghazadeh Mohandesi, Amirali
- Davenport, Mark A.
- Committee member dc:contributor.committeemember
-
- Staiculescu, Daniela
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/81670