Bayesian Convolutional Neural Networks for Compressed Sensing Restoration

Abstract

Deep Neural Networks (DNNs) have aroused great attention in Compressed Sensing (CS) restoration. However, the working mechanism of DNNs is not explainable, thereby it is unclear that how to design an optimal DNNs for CS restoration. In this paper, we propose a novel statistical framework to explain DNNs, which proves that the hidden layers of DNNs are equivalent to Gibbs distributions and interprets DNNs as a Bayesian hierarchical model. The framework provides a Bayesian perspective to explain the working mechanism of DNNs, namely some hidden layers learn a prior distribution and other layers learn a likelihood distribution. Moreover, the framework provides insights into DNNs and reveals two inherent limitations of DNNs for CS restoration. In contrast to most previous works designing an end-to-end DNNs for CS restoration, we propose a novel DNNs to model a prior distribution only, which can circumvent the limitations of DNNs. Given the prior distribution generated from the DNNs, we design a Bayesian inference algorithm to realize CS restoration in the framework of Bayesian Compressed Sensing. Finally, extensive simulations validate the proposed theory of DNNs and demonstrate that the proposed algorithm outperforms the state-of-the-art CS restoration methods.

References in corpus (12)

• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Conditional Random Fields as Recurrent Neural Networks
• Structured Compressed Sensing: From Theory to Applications
• Opening the Black Box of Deep Neural Networks via Information
• Expectation-Maximization Gaussian-Mixture Approximate Message Passing
• DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing
• Compressive Imaging using Approximate Message Passing and a Markov-Tree Prior
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• An exact mapping between the Variational Renormalization Group and Deep Learning
• Feature Denoising for Improving Adversarial Robustness
• Approximate Message Passing Algorithm with Universal Denoising and Gaussian Mixture Learning