Deep Learning Techniques for Compressive Sensing-Based Reconstruction and Inference -- A Ubiquitous Systems Perspective

2021/05/26 by Alina L. Machidon, Machidon, Alina L., Veljko Pejović +2 · 1 citation
Computer Science · Engineering · #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Microwave Imaging and Scattering Analysis #Photoacoustic and Ultrasonic Imaging #Signal Processing (eess.SP) #Sparse and Compressive Sensing Techniques #cs.LG #eess.SP #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2105.13191

arxiv created 2021/05/26 · openalex publication_date 2021/05/26 · arxiv updated 2021/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Compressive sensing (CS) is a mathematically elegant tool for reducing the sampling rate, potentially bringing context-awareness to a wider range of devices. Nevertheless, practical issues with the sampling and reconstruction algorithms prevent further proliferation of CS in real world domains, especially among heterogeneous ubiquitous devices. Deep learning (DL) naturally complements CS for adapting the sampling matrix, reconstructing the signal, and learning form the compressed samples. While the CS-DL integration has received substantial research interest recently, it has not yet been thoroughly surveyed, nor has the light been shed on practical issues towards bringing the CS-DL to real world implementations in the ubicomp domain. In this paper we identify main possible ways in which CS and DL can interplay, extract key ideas for making CS-DL efficient, identify major trends in CS-DL research space, and derive guidelines for future evolution of CS-DL within the ubicomp domain.

Citations

• An Iteration Formula for Fredholm Integral Equations of the First Kind
• Sparse Solution of Underdetermined Systems of Linear Equations by Stagewise Orthogonal Matching Pursuit
• Atomic Decomposition by Basis Pursuit
• Nonlinear total variation based noise removal algorithms
• Matching pursuits with time-frequency dictionaries
• Stable signal recovery from incomplete and inaccurate measurements
• CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
• A Deep Learning Approach to Block-based Compressed Sensing of Images
• Compressed Learning: A Deep Neural Network Approach
• Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
• Deep De-Aliasing for Fast Compressive Sensing MRI
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning
• Slimmable Neural Networks
• Application of Compressive Sensing Techniques in Distributed Sensor Networks: A Survey
• Iterative hard thresholding for compressed sensing
• Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing
• Learning Fast Approximations of Sparse Nonlinear Regression

Cited by

• Energy, Scalability, Data and Security in Massive IoT: Current Landscape and Future Directions

Related

• Deep Learning of Compressed Sensing Operators with Structural Similarity Loss
• Structured Compressed Sensing: From Theory to Applications
• Scalable Deep Compressive Sensing
• Error Resilient Deep Compressive Sensing
• Deep Blind Compressed Sensing