Related papers: Regularized Training of Intermediate Layers for Generative Models for Inverse Problems

Regularized Training of Intermediate Layers for Generative Models for Inverse Problems

URL: http://arxiv.org/abs/2203.04382v1
Date: Tue, 8 Mar 2022 20:30:49 GMT
Title: Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
Authors: Sean Gunn, Jorio Cocola, Paul Hand
Abstract summary: We introduce a principle that if a generative model is intended for inversion using an algorithm based on optimization of intermediate layers, it should be trained in a way that regularizes those intermediate layers. We instantiate this principle for two notable recent inversion algorithms: Intermediate Layer Optimization and the Multi-Code GAN prior. For both of these inversion algorithms, we introduce a new regularized GAN training algorithm and demonstrate that the learned generative model results in lower reconstruction errors across a wide range of under sampling ratios.
Score: 9.577509224534323
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation error, the fundamental limitation of the network in representing any particular signal. Recently, multiple proposed inversion algorithms reduce representation error by optimizing over intermediate layer representations. These methods are typically applied to generative models that were trained agnostic of the downstream inversion algorithm. In our work, we introduce a principle that if a generative model is intended for inversion using an algorithm based on optimization of intermediate layers, it should be trained in a way that regularizes those intermediate layers. We instantiate this principle for two notable recent inversion algorithms: Intermediate Layer Optimization and the Multi-Code GAN prior. For both of these inversion algorithms, we introduce a new regularized GAN training algorithm and demonstrate that the learned generative model results in lower reconstruction errors across a wide range of under sampling ratios when solving compressed sensing, inpainting, and super-resolution problems.