[1]SHAO Kai,YAN Lili,WANG Guangyu.Two-step deep unfolding strategy for compressed sensing reconstruction algorithms[J].CAAI Transactions on Intelligent Systems,2023,18(5):1117-1126.[doi:10.11992/tis.202204029]
Copy

Two-step deep unfolding strategy for compressed sensing reconstruction algorithms

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 18 Number of periods: 2023 5 Page number: 1117-1126 Column: 学术论文—机器学习 Public date: 2023-09-05
Title:
Two-step deep unfolding strategy for compressed sensing reconstruction algorithms
Author(s):
SHAO Kai1; 2; 3;  YAN Lili1;  WANG Guangyu1; 2; 3
1. School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
2. Chongqing Key Laboratory of Mobile Communications Technology, Chongqing 400065, China;
3. Engineering Research Center of Mobile Communications, Ministry of Education, Chongqing 400065, China
Keywords:
compressed sensing; sparse signal; signal reconstruction; deep learning; deep unfolding; model-driven; iterative soft threshold; approximate message passing algorithm; image processing
CLC:
TP399；TN911
DOI:
10.11992/tis.202204029
Abstract:
A two-step deep unfolding (TwDU) strategy is put forward for the deep unfolding of reconstruction algorithms in compressed sensing. The existing deep unfolding reconstruction algorithms usually estimate the current value based on the previous one-step estimated value. TwDU increases the estimation depth for the existing deep unfolding reconstruction algorithms and estimates the current unfolding value based on the previous two-step estimation value. TwDU increases two training weights for the previous two-step estimation value in the existing deep unfolding reconstruction algorithm. The training weights are self-adaptive, which can learn and adjust following the changes in data characteristics by themselves and optimize and utilize the correlation among the estimated signal values. The proposed TwDU strategy is applied to the existing deep unfolding reconstruction algorithms, such as the learned iterative soft thresholding algorithm, learned approximate message passing algorithm, and trainable iterative soft thresholding algorithm. The simulation results in one-dimensional and two-dimensional sparse signals confirm that the TwDU strategy has obvious advantages regarding reconstruction accuracy and convergence speed.
References:
[1] CANDES E J, ROMBERG J, TAO T. Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information[J]. IEEE transactions on information theory, 2006, 52(2): 489-509.
[2] DONOHO D L. Compressed sensing[J]. IEEE transactions on information theory, 2006, 52(4): 1289-1306.
[3] ZHANG Zheng, XU Yong, YANG Jian, et al. A survey of sparse representation: algorithms and applications[J]. IEEE access, 2015, 3: 490-530.
[4] CHAMBOLLE A, DE VORE R A, LEE N Y, et al. Nonlinear wavelet image processing: variational problems, compression, and noise removal through wavelet shrinkage[J]. IEEE transactions on image processing, 1998, 7(3): 319-335.
[5] BECK A, TEBOULLE M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J]. SIAM journal on imaging sciences, 2009, 2(1): 183-202.
[6] BIOUCAS-DIAS J M, FIGUEIREDO M A T. A new TwIST: two-step iterative shrinkage/thresholding algorithms for image restoration[J]. IEEE transactions on image processing, 2007, 16(12): 2992-3004.
[7] DONOHO D L, MALEKI A, MONTANARI A. Message-passing algorithms for compressed sensing[J]. Proceedings of the national academy of sciences of the United States of America, 2009, 106(45): 18914-18919.
[8] 许子微, 陈秀宏. 自步稀疏最优均值主成分分析[J]. 智能系统学报, 2016, 16(3): 416-424
XU Ziwei, CHEN Xiuhong. Sparse optimal mean principal component analysis based on self-paced learning[J]. CAAI transactions on intelligent systems, 2016, 16(3): 416-424
[9] 唐荣, 罗川, 曹潜, 等. 不完备数据中面向特征值更新的增量特征选择方法[J]. 智能系统学报, 2021, 16(3): 493-501
TANG Rong, LUO Chuan, CAO Qian, et al. Incremental approach for feature selection in incomplete data while updating feature values[J]. CAAI transactions on intelligent systems, 2021, 16(3): 493-501
[10] 窦勇敢, 袁晓彤. 基于隐式随机梯度下降优化的联邦学习[J]. 智能系统学报, 2022, 17(3): 488-495
DOU Yonggan, YUAN Xiaotong. Federated learning with implicit stochastic gradient descent optimization[J]. CAAI transactions on intelligent systems, 2022, 17(3): 488-495
[11] 包政凯, 朱齐丹, 刘永超. 满秩分解最小二乘法船舶航向模型辨识[J]. 智能系统学报, 2022, 17(1): 137-143
BAO Zhengkai, ZHU Qidan, LIU Yongchao. Ship heading model identification based on full rank decomposition least square method[J]. CAAI transactions on intelligent systems, 2022, 17(1): 137-143
[12] SHI Wuzhen, JIANG Feng, LIU Shiliang, et al. Image compressed sensing using convolutional neural network[J]. IEEE transactions on image processing, 2020, 29: 375-388.
[13] YAO Hantao, DAI Feng, ZHANG Shiliang, et al. DR2-Net: deep residual reconstruction network for image compressive sensing[J]. Neurocomputing, 2019, 359: 483-493.
[14] MOUSAVI A, BARANIUK R G. Learning to invert: signal recovery via deep convolutional networks[C]//2017 IEEE International Conference on Acoustics, Speech and Signal Processing. New Orleans: IEEE, 2017: 2272?2276.
[15] SAMUEL N, DISKIN T, WIESEL A. Learning to detect[J]. IEEE transactions on signal processing, 2019, 67(10): 2554-2564.
[16] 李晓辉, 王维猛, 黑永强. 基于空频相关的大规模MIMO-OFDM系统压缩信道反馈[J]. 电子与信息学报, 2014, 36(5): 1178-1183
LI Xiaohui, WANG Weimeng, HEI Yongqiang. Compressed channel feedback for large-scale MIMO-OFDM systems based on space frequency correlation[J]. Journal of Electronics and Information Technology, 2014, 36(5): 1178-1183
[17] 张博文. 基于自适应深度神经网络的稀疏线性逆问题研究及其在通信系统中的应用[D].北京: 北京交通大学, 2021: 12?29.
ZhANG Bowen. Research on Sparse Linear Inverse Problem Based on Adaptive Deep Neural Networks and Its Application in Communication Systems [D]. Beijing: Beijing Jiaotong University, 2021: 12?29.
[18] QIAN Qipeng, XIONG Fengchao, ZHOU Jun. Deep unfolded iterative shrinkage-thresholding model for hyperspectral unmixing[C]//2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama: IEEE, 2019: 2151?2154.
[19] VAN LUONG H, JOUKOVSKY B, ELDAR Y C, et al. A deep-unfolded reference-based RPCA network for video foreground-background separation[C]//2020 28th European Signal Processing Conference. Amsterdam: IEEE, 2020: 1432?1436.
[20] LIU Jiaming, SUN Yu, GAN Weijie, et al. Stochastic deep unfolding for imaging inverse problems[C]//2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Toronto: IEEE, 2021: 1395?1399.
[21] 马培旗, 袁玉山, 张宗夕, 等. 基于压缩感知技术三维MRI用于半月板损伤[J]. 中国医学影像技术, 2020, 36(10): 1533-1536
MA Peiqi, YUAN Yushan, ZHANG Zongxi, et al. 3D MRI based on compressed sensing technology for meniscus injury[J]. Chinese Medical Imaging Technology, 2020, 36(10): 1533-1536
[22] LIU Yiling, LIU Qiegen, ZHANG Minghui, et al. IFR-net: iterative feature refinement network for compressed sensing MRI[J]. IEEE transactions on computational imaging, 2020, 6: 434-446.
[23] SOLOMON O, COHEN R, ZHANG Yi, et al. Deep unfolded robust PCA with application to clutter suppression in ultrasound[J]. IEEE transactions on medical imaging, 2020, 39(4): 1051-1063.
[24] HERSHEY J R, LE ROUX J, WENINGER F. Deep unfolding: model-based inspiration of novel deep architectures[EB/OL]. (2014?09?09)[2020?01?01]. https://arxiv.org/abs/1409.2574.
[25] GREGOR K, LECUN Y. Learning fast approximations of sparse coding[J]. ICML 2010 - proceedings, 27th international conference on machine learning, 2010: 399?406.
[26] BORGERDING M, SCHNITER P. Onsager-corrected deep learning for sparse linear inverse problems[C]//2016 IEEE Global Conference on Signal and Information Processing. Washington, DC: IEEE, 2017: 227?231.
[27] ITO D, TAKABE S, WADAYAMA T. Trainable ISTA for sparse signal recovery[J]. IEEE transactions on signal processing, 2019, 67(12): 3113-3125.
[28] MONTANARI A. Graphical models concepts in compressed sensing[M]//Compressed Sensing. Cambridge: Cambridge University Press, 2012: 394?438.
[29] BORGERDING M, SCHNITER P, RANGAN S. AMP-inspired deep networks for sparse linear inverse problems[J]. IEEE transactions on signal processing, 2017, 65(16): 4293-4308.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems