Task-Aware Compressed Sensing with Generative Adversarial Networks

TL;DR

This paper introduces a novel approach using task-aware GANs to improve compressed sensing by replacing sparsity constraints, enabling effective reconstruction and classification with minimal non-compressed data.

Contribution

It proposes a task-aware training method for GANs in compressed sensing, allowing structure imposition without extensive non-compressed data and leveraging latent space for inference.

Findings

Effective reconstruction and classification demonstrated

Minimal non-compressed data required for training

Latent space contains useful discriminative information

Abstract

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.