基于超深残差通道注意力网络的图像压缩感知重构

doi:10.3969/j.issn.0255-8297.2022.06.001

摘要/Abstract

摘要： 提出了一种基于超深残差通道注意力网络的图像压缩感知重构算法。超深残差通道注意力网络的重构部分由多个残差组组成，每个残差组包含一个长连接和一组带有短连接的残差块。长连接结构能够有效传播丰富的低频信息，使主干网络专注于学习高频信息。在残差块中引入通道注意力机制，通过考虑通道间的相互依赖性来自适应地重新划分通道特征，从而达到强化重要特征的效果。实验表明，该算法能够有效提升图像压缩感知的重构精度。

关键词: 压缩感知, 图像重构, 残差组, 通道注意力

Abstract: An image compressive sensing reconstruction method based on ultra-deep residual channel attention networks is proposed. The reconstruction part of the ultra-deep residual channel attention network consists of multiple residual groups, each of which contains a long connection and a set of residual blocks with short connections. The long-connected structure can effectively deliver rich low-frequency information, allowing main network to focus on learning high-frequency information. The channel attention mechanism is introduced into residual blocks. By considering the interdependence between channels, the channel features keep changing adaptively so as to strengthen the important features. Experiments show that this method can effectively improve the reconstruction accuracy of image compressed sensing.

Key words: compressive sensing, image reconstruction, residual group, channel attention (CA)

中图分类号:

TN911.73

袁文杰, 田金鹏, 杨洁. 基于超深残差通道注意力网络的图像压缩感知重构[J]. 应用科学学报, 2022, 40(6): 887-895.

YUAN Wenjie, TIAN Jinpeng, YANG Jie. Image Compressive Sensing Reconstruction Using Ultra-Deep Residual Channel Attention Network[J]. Journal of Applied Sciences, 2022, 40(6): 887-895.

参考文献

[1] Candès E J. Compressive sampling[C]//Proceedings of the International Congress of Mathe-maticians, 2006:1433-1452.
[2] Donoho D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306.
[3] Liu Y P, Shan W, Huang X L, et al. Hybrid CS-DMRI:periodic time-variant subsampling and omnidirectional total variation based reconstruction[J]. IEEE Transaction on Medical Imaging, 2017, 36(10):2148-2159.
[4] Yuan X, Brady D J, Katsaggelos A K. Snapshot compressive imaging:theory, algorithms, and applications[J]. IEEE Signal Processing Magazine, 2021, 38(2):65-88.
[5] Li C B, Yin W, Zhang Y. User's guide for TVAL3:TV minimization by augmented Lagrangian and alternating direction algorithms[J]. Computer Science, 2010, 20(46/47):4.
[6] Zhang J, Zhao D B, Gao W. Group-based sparse representation for image restoration[J]. IEEE Transactions on Image Processing, 2014, 23(8):3336-3351.
[7] Chen C, Tramel E W, Fowler J E. Compressed-sensing recovery of images and video using multihypothesis predictions[C]//2011 Conference Record of the Forty-Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR), 2011:1193-1198.
[8] Metzler C A, Maleki A, Baraniuk R G. From denoising to compressed sensing[J]. IEEE Transactions on Information Theory, 2016, 62(9):5117-5144.
[9] Mousavi A, Patel A B, Baraniuk R G. A deep learning approach to structured signal recovery[C]//201553rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), 2015:1336-1343.
[10] Kulkarni K, Lohit S, Turaga P, et al. Reconnet:non-iterative reconstruction of images from compressively sensed measurements[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:449-458.
[11] Yao H T, Dai F, Zhang S L, et al. DR2-Net:deep residual reconstruction network for image compressive sensing[J]. Neurocomputing, 2019, 359:483-493.
[12] Zhang J, Ghanem B. ISTA-Net:interpretable optimization-inspired deep network for image compressive sensing[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018:1828-1837.
[13] Shi W Z, Jiang F, Zhang S P, et al. Deep networks for compressed image sensing[C]//2017 IEEE International Conference on Multimedia and Expo (ICME), 2017:877-882.
[14] Shi W Z, Jiang F, Liu S H, et al. Image compressed sensing using convolutional neural network[J]. IEEE Transaction Image Process, 2019, 29:375-388.
[15] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
[16] Baraniuk R, Davenport M, Devore R, et al. A simple proof of the restricted isometry property for random matrices[J]. Constructive Approximation, 2008, 28(3):253-263.
[17] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018:7132-7141.
[18] Zhang Y L, Li K P, Li K, et al. Image super-resolution using very deep residual channel attention networks[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018:286-301.
[19] Timofte R, Agustsson E, Gool V L, et al. Ntire 2017 challenge on single image superresolution:methods and results[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017:114-125.
[20] Bevilacqua M, Roumy A, Guillemot C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding[C]//The 23rd British Machine Vision Conference, 2012:135.1-135.10.
[21] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations[C]//International Conference on Curves and Surfaces, 2010:711-730.
[22] Martin D, Fowlkes C, Tal D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Proceedings Eighth IEEE International Conference on Computer Vision, 2001:416-423.