[HTML][HTML] A review of uncertainty quantification in deep learning: Techniques, applications and challenges

M Abdar, F Pourpanah, S Hussain, D Rezazadegan… - Information fusion, 2021 - Elsevier
Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Neural network-based processing and reconstruction of compromised biophotonic image data

MJ Fanous, P Casteleiro Costa, Ç Işıl… - Light: Science & …, 2024 - nature.com
In recent years, the integration of deep learning techniques with biophotonic setups has
opened new horizons in bioimaging. A compelling trend in this field involves deliberately …

Bayesian imaging using plug & play priors: when langevin meets tweedie

R Laumont, VD Bortoli, A Almansa, J Delon… - SIAM Journal on Imaging …, 2022 - SIAM
Since the seminal work of Venkatakrishnan, Bouman, and Wohlberg [Proceedings of the
Global Conference on Signal and Information Processing, IEEE, 2013, pp. 945--948] in …

Deep bayesian inversion

J Adler, O Öktem - arxiv preprint arxiv:1811.05910, 2018 - arxiv.org
Characterizing statistical properties of solutions of inverse problems is essential for decision
making. Bayesian inversion offers a tractable framework for this purpose, but current …

Deep probabilistic imaging: Uncertainty quantification and multi-modal solution characterization for computational imaging

H Sun, KL Bouman - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Computational image reconstruction algorithms generally produce a single image without
any measure of uncertainty or confidence. Regularized Maximum Likelihood (RML) and …

Fixed point strategies in data science

PL Combettes, JC Pesquet - IEEE Transactions on Signal …, 2021 - ieeexplore.ieee.org
The goal of this article is to promote the use of fixed point strategies in data science by
showing that they provide a simplifying and unifying framework to model, analyze, and solve …

Image reconstruction algorithms in radio interferometry: From handcrafted to learned regularization denoisers

M Terris, A Dabbech, C Tang… - Monthly Notices of the …, 2023 - academic.oup.com
We introduce a new class of iterative image reconstruction algorithms for radio
interferometry, at the interface of convex optimization and deep learning, inspired by plug …

Uncertainty calibrations of deep-learning schemes for full-wave inverse scattering problems

S He, G Zhang, Z Wei - IEEE Transactions on Geoscience and …, 2023 - ieeexplore.ieee.org
Recently, deep learning methods have attracted intensive attentions on solving inverse
scattering problems (ISPs). However, different with traditional physical-model-based …

Regularization, Bayesian inference, and machine learning methods for inverse problems

A Mohammad-Djafari - Entropy, 2021 - mdpi.com
Classical methods for inverse problems are mainly based on regularization theory, in
particular those, that are based on optimization of a criterion with two parts: a data-model …

Comparison of classical and Bayesian imaging in radio interferometry-Cygnus A with CLEAN and resolve

P Arras, HL Bester, RA Perley, R Leike… - Astronomy & …, 2021 - aanda.org
CLEAN, the commonly employed imaging algorithm in radio interferometry, suffers from a
number of shortcomings: In its basic version, it does not have the concept of diffuse flux, and …