Task-Aware Compressed Sensing with Generative Adversarial Networks
This addresses compressed sensing problems for applications like computer vision, offering a novel approach but appears incremental as it builds on existing GAN methods.
The paper tackles compressed sensing by using Generative Adversarial Networks (GANs) to impose structure instead of sparsity constraints, training them in a task-aware manner for reconstruction and showing effectiveness on various tasks.
In recent years, neural network approaches have been widely adopted for machine learning tasks, with applications in computer vision. More recently, unsupervised generative models based on neural networks have been successfully applied to model data distributions via low-dimensional latent spaces. In this paper, we use Generative Adversarial Networks (GANs) to impose structure in compressed sensing problems, replacing the usual sparsity constraint. We propose to train the GANs in a task-aware fashion, specifically for reconstruction tasks. We also show that it is possible to train our model without using any (or much) non-compressed data. Finally, we show that the latent space of the GAN carries discriminative information and can further be regularized to generate input features for general inference tasks. We demonstrate the effectiveness of our method on a variety of reconstruction and classification problems.