An inner-loop free solution to inverse problems using deep neural networks

09/06/2017
by   Qi Wei, et al.
0

We propose a new method that uses deep learning techniques to accelerate the popular alternating direction method of multipliers (ADMM) solution for inverse problems. The ADMM updates consist of a proximity operator, a least squares regression that includes a big matrix inversion, and an explicit solution for updating the dual variables. Typically, inner loops are required to solve the first two sub-minimization problems due to the intractability of the prior and the matrix inversion. To avoid such drawbacks or limitations, we propose an inner-loop free update rule with two pre-trained deep convolutional architectures. More specifically, we learn a conditional denoising auto-encoder which imposes an implicit data-dependent prior/regularization on ground-truth in the first sub-minimization problem. This design follows an empirical Bayesian strategy, leading to so-called amortized inference. For matrix inversion in the second sub-problem, we learn a convolutional neural network to approximate the matrix inversion, i.e., the inverse mapping is learned by feeding the input through the learned forward network. Note that training this neural network does not require ground-truth or measurements, i.e., it is data-independent. Extensive experiments on both synthetic data and real datasets demonstrate the efficiency and accuracy of the proposed method compared with the conventional ADMM solution using inner loops for solving inverse problems.

READ FULL TEXT

page 7

page 8

page 11

page 13

page 14

page 15

page 16

page 17

research
12/01/2017

InverseNet: Solving Inverse Problems with Splitting Networks

We propose a new method that uses deep learning techniques to solve the ...
research
11/03/2020

Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting

We mainly analyze and solve the overfitting problem of deep image prior ...
research
04/28/2021

Consensus ADMM for Inverse Problems Governed by Multiple PDE Models

The Alternating Direction Method of Multipliers (ADMM) provides a natura...
research
11/22/2022

Bayesian Inversion with Neural Operator (BINO) for Modeling Subdiffusion: Forward and Inverse Problems

Fractional diffusion equations have been an effective tool for modeling ...
research
09/06/2020

An Analysis of Alternating Direction Method of Multipliers for Feed-forward Neural Networks

In this work, we present a hardware compatible neural network training a...
research
07/04/2018

Learning Personalized Representation for Inverse Problems in Medical Imaging Using Deep Neural Network

Recently deep neural networks have been widely and successfully applied ...
research
07/20/2022

Deep Preconditioners and their application to seismic wavefield processing

Seismic data processing heavily relies on the solution of physics-driven...

Please sign up or login with your details

Forgot password? Click here to reset