Regularization by Architecture: A Deep Prior Approach for Inverse Problems

被引：70

作者：

Dittmer, Soren ^{[1
]}

Kluth, Tobias ^{[1
]}

Maass, Peter ^{[1
]}

Baguer, Daniel Otero ^{[1
]}

机构：

[1] Univ Bremen, Ctr Ind Math ZeTeM, Bremen, Germany

来源：

JOURNAL OF MATHEMATICAL IMAGING AND VISION | 2020年 / 62卷 / 03期

基金：

欧盟地平线“2020”;

关键词：

Inverse problems; Deep learning; Regularization by architecture; Deep inverse prior; Deep image prior; THRESHOLDING ALGORITHM; SPARSE;

D O I：

10.1007/s10851-019-00923-x

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The present paper studies so-called deep image prior (DIP) techniques in the context of ill-posed inverse problems. DIP networks have been recently introduced for applications in image processing; also first experimental results for applying DIP to inverse problems have been reported. This paper aims at discussing different interpretations of DIP and to obtain analytic results for specific network designs and linear operators. The main contribution is to introduce the idea of viewing these approaches as the optimization of Tikhonov functionals rather than optimizing networks. Besides theoretical results, we present numerical verifications.

引用

页码：456 / 470

页数：15

共 35 条

[1]

Abadi Martin, 2015, TensorFlow: Large-scale machine learning on heterogeneous systems

[2] Learned Primal-Dual Reconstruction [J].