Naslov
Deep Variational Inverse Scattering

Autori
Khorashadizadeh, AmirEhsan ; Aghababaei, Ali ; Vlašić, Tin ; Nguyen Hieu ; Dokmanić, Ivan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 2023 17th European Conference on Antennas and Propagation (EuCAP) / - , 2023, 1-5

Skup
2023 17th European Conference on Antennas and Propagation (EuCAP)

Mjesto i datum
Firenca, Italija, 26.03.2023. - 31.03.2023

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Bayesian inference ; conditional normalizing flow ; inverse scattering ; U-Net

Sažetak
Inverse medium scattering solvers generally reconstruct a single solution without an associated measure of uncertainty. This is true both for the classical iterative solvers and for the emerging deep-learning methods. But ill-posedness and noise can make this single estimate inaccurate or misleading. While deep networks such as conditional normalizing flows can be used to sample posteriors in inverse problems, they often yield low-quality samples and uncertainty estimates. In this paper, we propose U-Flow, a Bayesian U-Net based on conditional normalizing flows, which generates high- quality posterior samples and estimates physically-meaningful uncertainty. We show that the proposed model significantly outperforms the recent normalizing flows in terms of posterior sample quality while having comparable performance with the U-Net in point estimation.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA