Deep Compressed Sensing

TL;DR

This paper introduces a new deep learning framework for compressed sensing that enhances recovery performance and speed by jointly training generators and reconstruction processes through meta-learning, integrating GANs insights.

Contribution

It presents a novel joint training approach for signal recovery that combines neural networks and meta-learning, improving over traditional sparse recovery methods.

Findings

Enhanced recovery accuracy and speed demonstrated

Meta-learning improves reconstruction robustness

GANs can be integrated into the compressed sensing framework

Abstract

Compressed sensing (CS) provides an elegant framework for recovering sparse signals from compressed measurements. For example, CS can exploit the structure of natural images and recover an image from only a few random measurements. CS is flexible and data efficient, but its application has been restricted by the strong assumption of sparsity and costly reconstruction process. A recent approach that combines CS with neural network generators has removed the constraint of sparsity, but reconstruction remains slow. Here we propose a novel framework that significantly improves both the performance and speed of signal recovery by jointly training a generator and the optimisation process for reconstruction via meta-learning. We explore training the measurements with different objectives, and derive a family of models based on minimising measurement errors. We show that Generative Adversarial Nets (GANs) can be viewed as a special case in this family of models. Borrowing insights from the CS perspective, we develop a novel way of improving GANs using gradient information from the discriminator.