Výsledky vyhledávání - "Arndt, Clemens"

Report

Invertible ResNets for Inverse Imaging Problems: Competitive Performance with Provable Regularization Properties

Learning-based methods have demonstrated remarkable performance in solving inverse problems, particularly in image reconstruction tasks. Despite their success, these approaches often lack theoretical guarantees, which are crucial in sensitive applica

Externí odkaz: http://arxiv.org/abs/2409.13482

Zobrazit plný text záznamu

Report

Bayesian view on the training of invertible residual networks for solving linear inverse problems

Autor: Arndt, Clemens, Dittmer, Sören, Heilenkötter, Nick, Iske, Meira, Kluth, Tobias, Nickel, Judith

Learning-based methods for inverse problems, adapting to the data's inherent structure, have become ubiquitous in the last decade. Besides empirical investigations of their often remarkable performance, an increasing number of works addresses the iss

Externí odkaz: http://arxiv.org/abs/2307.10431

Zobrazit plný text záznamu

Report

Invertible residual networks in the context of regularization theory for linear inverse problems

Autor: Arndt, Clemens, Denker, Alexander, Dittmer, Sören, Heilenkötter, Nick, Iske, Meira, Kluth, Tobias, Maass, Peter, Nickel, Judith

Publikováno v: Inverse Problems 39 125018 (2023)

Learned inverse problem solvers exhibit remarkable performance in applications like image reconstruction tasks. These data-driven reconstruction methods often follow a two-step scheme. First, one trains the often neural network-based reconstruction s

Externí odkaz: http://arxiv.org/abs/2306.01335

Zobrazit plný text záznamu

Report

Regularization Theory of the Analytic Deep Prior Approach

Autor: Arndt, Clemens

Publikováno v: Inverse Problems 38 115005 (2022)

The analytic deep prior (ADP) approach was recently introduced for the theoretical analysis of deep image prior (DIP) methods with special network architectures. In this paper, we prove that ADP is in fact equivalent to classical variational Ivanov m

Externí odkaz: http://arxiv.org/abs/2205.06493

Zobrazit plný text záznamu