Litcius/Paper detail

Deep Unfolding With Weighted <i>ℓ</i>₂ Minimization for Compressive Sensing

Jun Zhang, Yuanqing Li, Zhu Liang Yu, Zhenghui Gu, Yu Cheng, Huoqing Gong

2020IEEE Internet of Things Journal16 citationsDOI

Abstract

Compressive sensing (CS) aims to accurately reconstruct high-dimensional signals from a small number of measurements by exploiting signal sparsity and structural priors. However, signal priors utilized in existing CS reconstruction algorithms rely mainly on hand-crafted design, which often cannot offer the best sparsity-undersampling tradeoff because high-order structural priors of signals are hard to be captured in this manner. In this article, a new recovery guarantee of the unified CS reconstruction model-weighted ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> minimization (WL1M) is derived, which indicates universal priors could hardly lead to the optimal selection of the weights. Motivated by the analysis, we propose a deep unfolding network for the general WL1M model. The proposed deep unfolding-based WL1M (D-WL1M) integrates universal priors with learning capability so that all of the parameters, including the crucial weights, can be learned from training data. We demonstrate the proposed D-WL1M outperforms several state-of-the-art CS-based methods and deep learning-based methods by a large margin via the experiments on the Caltech-256 image data set.

Topics & Concepts

Prior probabilityCompressed sensingUndersamplingComputer scienceMinificationArtificial intelligenceMargin (machine learning)Prior informationDeep learningSignal reconstructionAlgorithmPattern recognition (psychology)Machine learningSignal processingBayesian probabilityRadarTelecommunicationsProgramming languageSparse and Compressive Sensing TechniquesMicrowave Imaging and Scattering AnalysisUltrasound Imaging and Elastography