Deep learning approaches for sparse recovery in compressive sensing

E. C. Marques, N. Maciel, L. Naviner, H. Cai, J. Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Compressive sensing enables sparse signals recovery by less measurements than required by the Nyquist rate, so leading to energy and processing saving. Accuracy and complexity improvements can be achieved applying neural network to sparse linear inverse problem. This work focuses on sparse recovery with deep network. Improvements to the Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) and a novel neural network are proposed. Results show that these propositions can decrease up to 10.8 dB the NMSE value and require fewer layers than if only LISTA is used to estimate the signal.

Original languageEnglish
Title of host publicationISPA 2019 - 11th International Symposium on Image and Signal Processing and Analysis
EditorsSven Loncaric, Robert Bregovic, Marco Carli, Marko Subasic
PublisherIEEE Computer Society
Pages129-134
Number of pages6
ISBN (Electronic)9781728131405
DOIs
Publication statusPublished - 1 Sept 2019
Event11th International Symposium on Image and Signal Processing and Analysis, ISPA 2019 - Dubrovnik, Croatia
Duration: 23 Sept 201925 Sept 2019

Publication series

NameInternational Symposium on Image and Signal Processing and Analysis, ISPA
Volume2019-September
ISSN (Print)1845-5921
ISSN (Electronic)1849-2266

Conference

Conference11th International Symposium on Image and Signal Processing and Analysis, ISPA 2019
Country/TerritoryCroatia
CityDubrovnik
Period23/09/1925/09/19

Keywords

  • Compressive Sensing
  • Deep Network
  • Learned Iterative Shrinkage-Thresholding Algorithm
  • Sparse Recovery

Fingerprint

Dive into the research topics of 'Deep learning approaches for sparse recovery in compressive sensing'. Together they form a unique fingerprint.

Cite this