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

Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

Barbano, R; Kereta, Z; Zhang, C; Hauptmann, A; Arridge, SR; Jin, B; (2020) Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction. In: Proceedings of the NeurIPS 2020 Workshop on Deep Learning and Inverse Problems. (pp. pp. 1-13). NeurIPS Green open access

[img]
Preview
Text
Jin_Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction_VoR.pdf - Published version

Download (2MB) | Preview

Abstract

mage reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art of conventional approaches, but often do not provide uncertainty information of the reconstruction. In this work we propose a scalable and efficient framework to simultaneously quantify aleatoric and epistemic uncertainties in learned iterative image reconstruction. We build on a Bayesian deep gradient descent method for quantifying epistemic uncertainty, and incorporate heteroscedastic variance of the noise to account for the aleatoric uncertainty. We show that it exhibits competitive performance with respect to conventional benchmarks for computed tomography with both sparse view and limited angle data. The estimated uncertainty captures the variability in the reconstructions, caused by the restricted measurement model, and by missing information, due to the limited angle geometry.

Type: Proceedings paper
Title: Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction
Event: NeurIPS 2020 Workshop on Deep Learning and Inverse Problems
Location: Online
Dates: 11th December 2020
Open access status: An open access version is available from UCL Discovery
Publisher version: https://openreview.net/forum?id=iUGcSYdJogv
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Image Reconstruction, Uncertainty Quantification, Uncertainty Decoupling, BNNs, VI
UCL classification: UCL
UCL > Provost and Vice Provost Offices
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/10115553
Downloads since deposit
12Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item