Deep Compressed Sensing
This work addresses the costly reconstruction process in compressed sensing, which is a bottleneck for applications in signal processing and imaging, though it appears incremental by building on existing neural network approaches.
The paper tackles the problem of slow and performance-limited signal recovery in compressed sensing by proposing a meta-learning framework that jointly trains a generator and the optimization process, resulting in significant improvements in both speed and performance.
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.