Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Barbano, Riccardo"'
Autor:
Sabanza-Gil, Víctor, Barbano, Riccardo, Gutiérrez, Daniel Pacheco, Luterbacher, Jeremy S., Hernández-Lobato, José Miguel, Schwaller, Philippe, Roch, Loïc
Multi-fidelity Bayesian Optimization (MFBO) is a promising framework to speed up materials and molecular discovery as sources of information of different accuracies are at hand at increasing cost. Despite its potential use in chemical tasks, there is
Externí odkaz:
http://arxiv.org/abs/2410.00544
DEFT: Efficient Finetuning of Conditional Diffusion Models by Learning the Generalised $h$-transform
Autor:
Denker, Alexander, Vargas, Francisco, Padhy, Shreyas, Didi, Kieran, Mathis, Simon, Dutordoir, Vincent, Barbano, Riccardo, Mathieu, Emile, Komorowska, Urszula Julia, Lio, Pietro
Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained unconditional
Externí odkaz:
http://arxiv.org/abs/2406.01781
Autor:
Barbano, Riccardo, Denker, Alexander, Chung, Hyungjin, Roh, Tae Hoon, Arridge, Simon, Maass, Peter, Jin, Bangti, Ye, Jong Chul
Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored challenge.
Externí odkaz:
http://arxiv.org/abs/2308.14409
Autor:
Singh, Imraj RD, Denker, Alexander, Barbano, Riccardo, Kereta, Željko, Jin, Bangti, Thielemans, Kris, Maass, Peter, Arridge, Simon
Publikováno v:
Machine.Learning.for.Biomedical.Imaging. 2 (2024)
Score-based generative models have demonstrated highly promising results for medical image reconstruction tasks in magnetic resonance imaging or computed tomography. However, their application to Positron Emission Tomography (PET) is still largely un
Externí odkaz:
http://arxiv.org/abs/2308.14190
Autor:
Nittscher, Marco, Lameter, Michael, Barbano, Riccardo, Leuschner, Johannes, Jin, Bangti, Maass, Peter
The deep image prior (DIP) is a well-established unsupervised deep learning method for image reconstruction; yet it is far from being flawless. The DIP overfits to noise if not early stopped, or optimized via a regularized objective. We build on the
Externí odkaz:
http://arxiv.org/abs/2303.15748
Autor:
Barbano, Riccardo, Antorán, Javier, Leuschner, Johannes, Hernández-Lobato, José Miguel, Jin, Bangti, Kereta, Željko
Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill th
Externí odkaz:
http://arxiv.org/abs/2302.10279
Autor:
Antorán, Javier, Padhy, Shreyas, Barbano, Riccardo, Nalisnick, Eric, Janz, David, Hernández-Lobato, José Miguel
Large-scale linear models are ubiquitous throughout machine learning, with contemporary application as surrogate models for neural network uncertainty quantification; that is, the linearised Laplace method. Alas, the computational cost associated wit
Externí odkaz:
http://arxiv.org/abs/2210.04994
Autor:
Barbano, Riccardo, Leuschner, Johannes, Antorán, Javier, Jin, Bangti, Hernández-Lobato, José Miguel
We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach using the linearised deep image prior. It allows incorporating informa
Externí odkaz:
http://arxiv.org/abs/2207.05714
Autor:
Antorán, Javier, Janz, David, Allingham, James Urquhart, Daxberger, Erik, Barbano, Riccardo, Nalisnick, Eric, Hernández-Lobato, José Miguel
The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community. The method provides reliable error bars and admits a closed-form expression for the model evidence, allowing for sc
Externí odkaz:
http://arxiv.org/abs/2206.08900
Autor:
Antorán, Javier, Barbano, Riccardo, Leuschner, Johannes, Hernández-Lobato, José Miguel, Jin, Bangti
Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty, hindering their real-world deployment. This paper develops a method, termed as the linearised deep image prior (DIP
Externí odkaz:
http://arxiv.org/abs/2203.00479