Application-driven Validation of Posteriors in Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adler, Tim J., Nölke, Jan-Hinrich, Reinke, Annika, Tizabi, Minu Dietlinde, Gruber, Sebastian, Trofimova, Dasha, Ardizzone, Lynton, Jaeger, Paul F., Buettner, Florian, Köthe, Ullrich, Maier-Hein, Lena
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917908883439616
author Adler, Tim J.
Nölke, Jan-Hinrich
Reinke, Annika
Tizabi, Minu Dietlinde
Gruber, Sebastian
Trofimova, Dasha
Ardizzone, Lynton
Jaeger, Paul F.
Buettner, Florian
Köthe, Ullrich
Maier-Hein, Lena
author_facet Adler, Tim J.
Nölke, Jan-Hinrich
Reinke, Annika
Tizabi, Minu Dietlinde
Gruber, Sebastian
Trofimova, Dasha
Ardizzone, Lynton
Jaeger, Paul F.
Buettner, Florian
Köthe, Ullrich
Maier-Hein, Lena
contents Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, posterior-based methods such as conditional Diffusion Models and Invertible Neural Networks have emerged; however, their translation is hampered by a lack of research on adequate validation. In other words, the way progress is measured often does not reflect the needs of the driving practical application. Closing this gap in the literature, we present the first systematic framework for the application-driven validation of posterior-based methods in inverse problems. As a methodological novelty, it adopts key principles from the field of object detection validation, which has a long history of addressing the question of how to locate and match multiple object instances in an image. Treating modes as instances enables us to perform mode-centric validation, using well-interpretable metrics from the application perspective. We demonstrate the value of our framework through instantiations for a synthetic toy example and two medical vision use cases: pose estimation in surgery and imaging-based quantification of functional tissue parameters for diagnostics. Our framework offers key advantages over common approaches to posterior validation in all three examples and could thus revolutionize performance assessment in inverse problems.
format Preprint
id arxiv_https___arxiv_org_abs_2309_09764
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Application-driven Validation of Posteriors in Inverse Problems
Adler, Tim J.
Nölke, Jan-Hinrich
Reinke, Annika
Tizabi, Minu Dietlinde
Gruber, Sebastian
Trofimova, Dasha
Ardizzone, Lynton
Jaeger, Paul F.
Buettner, Florian
Köthe, Ullrich
Maier-Hein, Lena
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, posterior-based methods such as conditional Diffusion Models and Invertible Neural Networks have emerged; however, their translation is hampered by a lack of research on adequate validation. In other words, the way progress is measured often does not reflect the needs of the driving practical application. Closing this gap in the literature, we present the first systematic framework for the application-driven validation of posterior-based methods in inverse problems. As a methodological novelty, it adopts key principles from the field of object detection validation, which has a long history of addressing the question of how to locate and match multiple object instances in an image. Treating modes as instances enables us to perform mode-centric validation, using well-interpretable metrics from the application perspective. We demonstrate the value of our framework through instantiations for a synthetic toy example and two medical vision use cases: pose estimation in surgery and imaging-based quantification of functional tissue parameters for diagnostics. Our framework offers key advantages over common approaches to posterior validation in all three examples and could thus revolutionize performance assessment in inverse problems.
title Application-driven Validation of Posteriors in Inverse Problems
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2309.09764