Regularization of Inverse Problems: Deep Equilibrium Models versus Bilevel Learning

Abstract

Variational regularization methods are commonly used to approximate solutions of inverse problems. In recent years, model-based variational regularization methods have often been replaced with data-driven ones such as the fields-of-expert model (Roth and Black, 2009). Training the parameters of such data-driven methods can be formulated as a bilevel optimization problem. In this paper, we compare the framework of bilevel learning for the training of data-driven variational regularization models with the novel framework of deep equilibrium models (Bai, Kolter, and Koltun, 2019) that has recently been introduced in the context of inverse problems (Gilton, Ongie, and Willett, 2021). We show that computing the lower-level optimization problem within the bilevel formulation with a fixed point iteration is a special case of the deep equilibrium framework. We compare both approaches computationally, with a variety of numerical examples for the inverse problems of denoising, inpainting and deconvolution.

References in corpus (7)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Solving ill-posed inverse problems using iterative deep neural networks
• Insights into analysis operator learning: From patch-based sparse models to higher-order MRFs
• Fixed Point Strategies in Data Science
• Bilevel parameter learning for higher-order total variation regularisation models
• The structure of optimal parameters for image restoration problems
• Measuring the Accuracy of Object Detectors and Trackers