Generative Model Adversarial Training for Deep Compressed Sensing

Abstract

Deep compressed sensing assumes the data has sparse representation in a latent space, i.e., it is intrinsically of low-dimension. The original data is assumed to be mapped from a low-dimensional space through a low-to-high-dimensional generator. In this work, we propound how to design such a low-to-high dimensional deep learning-based generator suiting for compressed sensing, while satisfying robustness to universal adversarial perturbations in the latent domain. We also justify why the noise is considered in the latent space. The work is also buttressed with theoretical analysis on the robustness of the trained generator to adversarial perturbations. Experiments on real-world datasets are provided to substantiate the efficacy of the proposed \emph{generative model adversarial training for deep compressed sensing.}

References in corpus (8)

• Generative Adversarial Network in Medical Imaging: A Review
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Compressed Sensing with Deep Image Prior and Learned Regularization
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Deep Compressed Sensing
• Iterative Null-space Projection Method with Adaptive Thresholding in Sparse Signal Recovery and Matrix Completion
• Transduction with Matrix Completion Using Smoothed Rank Function