Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
复制标题
DOI：
10.48550/arxiv.2203.04382
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Sean Gunn;Jorio Cocola;Paul Hand
中科院分区：
文献类型：
--
作者：
Sean Gunn;Jorio Cocola;Paul Hand
生成对抗网络（GAN）在解决逆问题时已被证明是强大而灵活的先验。使用它们的一个挑战是克服表示误差，这是网络表示任何特定信号的基本限制。最近，多个提出的反演算法通过优化中间层表示来减少表示误差。这些方法通常应用于生成模型，该生成模型被训练为与下游反演算法无关。在我们的工作中，我们引入了一个原则，即如果生成模型旨在使用基于中间层优化的算法进行反演，则应该以正则化这些中间层的方式进行训练。我们实例化这一原则的两个显着的最近的反演算法：中间层优化和多代码GAN先验。对于这两种反演算法，我们引入了一种新的正则化GAN训练算法，并证明了在解决压缩感知、修复和超分辨率问题时，学习的生成模型在宽范围的欠采样率下都能降低重建误差。
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.