R
Riccardo Barbano
Researcher at University College London
Publications - 20
Citations - 77
Riccardo Barbano is an academic researcher from University College London. The author has contributed to research in topics: Computer science & Iterative reconstruction. The author has an hindex of 2, co-authored 10 publications receiving 16 citations.
Papers
More filters
Proceedings ArticleDOI
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Javier Antor'an,David Janz,James Urquhart Allingham,Erik Daxberger,Riccardo Barbano,Eric Nalisnick,Jos'e Miguel Hern'andez-Lobato +6 more
TL;DR: The assumptions behind the linearised Laplace method for estimating model uncertainty are examined, showing that these interact poorly with some now-standard tools of deep learning—stochastic approximation methods and normalisation layers—and make recommendations for how to better adapt this classic method to the modern setting.
Posted Content
Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent
TL;DR: A scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks, and builds on, and extends deep gradient descent, a recently developed greedy iterative training scheme, and recasts it within a probabilistic framework.
Supplementary Material for "Is Deep Image Prior in Need of a Good Education?"
TL;DR: This work develops a two-stage learning paradigm to address the computational challenge: (i) a supervised pretraining of the network on a synthetic dataset; (ii) it fine-tune the network’s parameters to adapt to the target reconstruction.
Journal ArticleDOI
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
Riccardo Barbano,Johannes Leuschner,Javier Antor'an,Bangti Jin,Jos'e Miguel Hern'andez-Lobato +4 more
TL;DR: This work proposes a novel approach using the linearised deep image prior that allows incorporating information from the pilot measurements into the angle selection criteria, while maintaining the tractability of a conjugate Gaussian-linear model.
Journal ArticleDOI
A Probabilistic Deep Image Prior for Computational Tomography
Javier Antor'an,Riccardo Barbano,Johannes Leuschner,Jos'e Miguel Hern'andez-Lobato,Bangti Jin +4 more
TL;DR: A Bayesian prior is constructed for tomographic reconstruction, which combines the classical total variation (TV) regulariser with the modern deep image prior (DIP), and an approach based on the linearised Laplace method is developed, which is scalable to highdimensional settings.