UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent

Barbano, R; Zhang, C; Arridge, SR; Jin, B; (2020) Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR). (pp. pp. 1392-1399). IEEE: Milan, Italy. Green open access

[thumbnail of Jin_2007.09971v2.pdf]
Preview
Text
Jin_2007.09971v2.pdf - Accepted version

Download (1MB) | Preview

Abstract

Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do not provide uncertainty on the obtained reconstruction. In this work, we develop a scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks. The approach builds on, and extends deep gradient descent, a recently developed greedy iterative training scheme, and recasts it within a probabilistic framework. Scalability is achieved by being hybrid in the architecture: only the last layer of each block is Bayesian, while the others remain deterministic, and by being greedy in training. The framework is showcased on one representative medical imaging modality, viz. computed tomography with either sparse view or limited view data, and exhibits competitive performance with respect to state-of-the-art benchmarks, e.g., total variation, deep gradient descent and learned primal-dual.

Type: Proceedings paper
Title: Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent
Event: 2020 25th International Conference on Pattern Recognition (ICPR)
ISBN-13: 978-1-7281-8808-9
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICPR48806.2021.9412521
Publisher version: https://doi.org/10.1109/ICPR48806.2021.9412521
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Training, Uncertainty, Inverse problems, Computational modeling, Scalability, Neural networks, Reconstruction algorithms
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10128436
Downloads since deposit
14Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item