LEARNING TO SAMPLE FOR SPARSE SIGNALS

被引:1
作者
Mulleti, Satish [1 ]
Zhang, Haiyang [1 ]
Eldar, Yonina C. [1 ]
机构
[1] Weizmann Inst Sci, Fac Math & Comp Sci, Rehovot, Israel
来源
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2022年
基金
欧洲研究理事会;
关键词
Finite rate of innovation signal; sub-Nyquist sampling; greedy algorithm; learn to sample; FINITE-RATE; RECONSTRUCTION; EFFICIENT; ALGORITHM;
D O I
10.1109/ICASSP43922.2022.9747815
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Finite-rate-of-innovation (FRI) signals are ubiquitous in radar, ultrasound, and time of flight imaging applications. In this paper, we propose a model-based deep learning approach to jointly design the subsampling and reconstruction of FRI signals. Specifically, our framework is a combination of a greedy subsampling algorithm and a learning-based sparse recovery method. Unlike existing learning-based techniques, the proposed algorithm can flexibly handle changes in the sampling rate and does not suffer from differentiability issues during training. Moreover, exact knowledge of the FRI pulse is not required. Numerical results show that the proposed joint design leads to lower reconstruction error for FRI signals compared with existing benchmark methods for a given number of samples. The method can easily adapt to other sparse recovery problems.
引用
收藏
页码:3363 / 3367
页数:5
相关论文
共 26 条
[11]  
LeCun, 2010, P 27 INT C INT C MAC, P399
[12]  
Leung V. C. H., 2021, P EUR SIGN PROC C EU
[13]  
Leung VCH, 2020, INT CONF ACOUST SPEE, P5430, DOI [10.1109/icassp40776.2020.9053383, 10.1109/ICASSP40776.2020.9053383]
[14]   Convolutional Neural Networks for Noniterative Reconstruction of Compressively Sensed Images [J].
Lohit, Suhas ;
Kulkarni, Kuldeep ;
Kerviche, Ronan ;
Turaga, Pavan ;
Ashok, Amit .
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2018, 4 (03) :326-340
[15]   Sparse MRI: The application of compressed sensing for rapid MR imaging [J].
Lustig, Michael ;
Donoho, David ;
Pauly, John M. .
MAGNETIC RESONANCE IN MEDICINE, 2007, 58 (06) :1182-1195
[16]   Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing [J].
Monga, Vishal ;
Li, Yuelong ;
Eldar, Yonina C. .
IEEE SIGNAL PROCESSING MAGAZINE, 2021, 38 (02) :18-44
[17]  
Mulleti S., 2020, P IEEE RAD C RADARCO
[18]   Paley-Wiener Characterization of Kernels for Finite-Rate-of-Innovation Sampling [J].
Mulleti, Satish ;
Seelamantula, Chandra Sekhar .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (22) :5860-5872
[19]   ANALYSIS OF APPROXIMATIONS FOR MAXIMIZING SUBMODULAR SET FUNCTIONS .1. [J].
NEMHAUSER, GL ;
WOLSEY, LA ;
FISHER, ML .
MATHEMATICAL PROGRAMMING, 1978, 14 (03) :265-294
[20]   Distributed Compressive Sensing: A Deep Learning Approach [J].
Palangi, Hamid ;
Ward, Rabab ;
Deng, Li .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2016, 64 (17) :4504-4518