To address the issue of texture detail blurring in single-scale sampled compressed sensing image reconstruction at low sampling rates and achieve a lightweight reconstruction network, this paper proposes a filter pruning based multi-scale compressed sensing image reconstruction network. In the sampling phase, the image is linearly decomposed by convolution, and then fused with the input image and different scale decomposition features to obtain the compressed sensing measurements. In the reconstruction phase, a coordinate attention based multi-scale dilated residual module is designed, which incorporates positional information into channel attention to enhance the feature learning ability of the network. Moreover, by calculating the entropy of the feature map to judge the importance of the filters, the less important filters is pruned to achieve the purpose of compressing the model. Training and testing are carried out on datasets such as DIV2K, Set5, BSDS68 and Urban100. The experimental results show that the algorithm proposed improves the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity(SSIM), and image visual effects. For instance, with a sampling rate of 4% and a test set of Set14, the proposed algorithm improves the PSNR of the reconstructed image by 4.17 dB and 2.39 dB, respectively, compared with CSNet+ and FSOINet, resulting in clearer texture details. Under the premise of slightly reducing the reconstruction effect, a lighter model was obtained, which improved the reconstruction speed.
WANGJ L, ZHOUS W, JINC C. Method of deep learning image compressed sensing based on adversarial samples[J]. Journal of Hunan University (Natural Sciences), 2022, 49(4): 11-17.(in Chinese)
ZHONGY H, ZHOUY J, ZHANGJ,et al. Deep compressive sensing image reconstruction network based on non-local prior[J]. Journal of Electronics & Information Technology,2023, 45(2):654-663.(in Chinese)
WANGL, WANGW, LIUB N .Hermitian compressed sensing reconstruction algorithm for hyperspectral images[J]. Laser & Optoelectronics Progress,2020,57(14):141032.(in Chinese)
[12]
TROPPJ A, GILBERTA C .Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory,2007,53(12):4655-4666.
[13]
BLUMENSATHT, DAVIESM E .Iterative hard thresholding for compressed sensing[J].Applied and Computational Harmonic Analysis,2009,27(3):265-274.
[14]
FIGUEIREDOM A T, NOWAKR D, WRIGHTS J .Gradient projection for sparse reconstruction:application to compressed sensing and other inverse problems[J].IEEE Journal of Selected Topics in Signal Processing,2007,1(4):586-597.
[15]
MOUSAVIA, PATELA B, BARANIUKR G .A deep learning approach to structured signal recovery[C]//2015 53rd Annual Allerton Conference on Communication,Control,and Computing (Allerton).Monticello,IL,USA. IEEE,2015:1336-1343.
LIANQ S, FUL P, CHENS Z,et al .A compressed sensing algorithm based on multi-scale residual reconstruction network[J]. Acta Automatica Sinica,2019,45(11):2082-2091.(in Chinese)
[18]
ZHOUS W, HEY, LIUY H, et al .Multi-channel deep networks for block-based image compressive sensing[J]. IEEE Transactions on Multimedia,2021,23:2627-2640.
[19]
KULKARNIK, LOHITS, TURAGAP,et al .ReconNet:non-iterative reconstruction of images from compressively sensed measurements[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA. IEEE,2016:449-458.
[20]
SHIW Z, JIANGF, LIUS H,et al .Image compressed sensing using convolutional neural network[J].IEEE Transactions on Image Processing, 2020, 29:375-388.
[21]
CUIW X, LIUS H, JIANGF,et al .Image compressed sensing using non-local neural network[J]. IEEE Transactions on Multimedia,2023,25:816-830.
[22]
ZHANGJ, GHANEMB .ISTA-net:interpretable optimization-inspired deep network for image compressive sensing[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA. IEEE,2018:1828-1837.
[23]
ZHANGJ, ZHAOC, GAOW .Optimization-inspired compact deep compressive sensing[J].IEEE Journal of Selected Topics in Signal Processing,2020,14(4):765-774.
[24]
CHENW J, YANGC L, YANGX .FSOINET:feature-space optimization-inspired network for image compressive sensing[C]//ICASSP 2022—2022 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Singapore,Singapore. IEEE,2022:2460-2464.
[25]
WEID Y, WANGZ W .Multi-scale channel network based on filer pruning for image super-resolution[J].Optik,2021,236:166641.
[26]
DENILM, SHAKIBIB, DINHL,et al .Predicting parameters in deep learning[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2.Lake Tahoe,Nevada. ACM,2013:2148-2156.
[27]
YANGT J, CHENY H,SZE V .Designing energy-efficient convolutional neural networks using energy-aware pruning[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA. IEEE,2017:6071-6079.
CANHT N, JEONB .Multi-scale deep compressive sensing network[C]//2018 IEEE Visual Communications and Image Processing (VCIP).Taichung,Taiwan,China. IEEE,2018:1-4.
[30]
SHIW Z, JIANGF, ZHANGS P,et al .Deep networks for compressed image sensing[C]//2017 IEEE International Conference on Multimedia and Expo (ICME). Hong Kong, China. IEEE, 2017: 877-882.
[31]
SHIW Z, JIANGF, LIUS H,et al .Multi-scale deep networks for image compressed sensing[C]//2018 25th IEEE International Conference on Image Processing (ICIP). Athens, Greece. IEEE,2018:46-50.
[32]
WANGZ B, QINY L, ZHENGH,et al .Multiscale deep network for compressive sensing image reconstruction[J].Journal of Electronic Imaging,2022,31:013025.
[33]
TUY, WANGM Y, WANGS .A data-driven deep neural network pruning approach towards efficient digital signal modulation recognition[C]//2019 IEEE Globecom Workshops (GC Wkshps).Waikoloa,HI,USA. IEEE,2019:1-5.
WANGC L, WANGJ, JIANGG P .Global adaptive filter pruning based on dual DDPG[J].Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition),2021,41(5):59-66.(in Chinese)
LINJ D, WUX Y, CHAIY,et al .Structure optimization of convolutional neural networks:a survey[J].Acta Automatica Sinica,2020,46(1):24-37.(in Chinese)
[40]
LIH, KADAVA, DURDANOVICI, et al. Pruning filters for efficient convNets [C]// Proceedings of the 5th International Conference on Learning Representations (ICLR). Toulon, France, 2017:128-140.
[41]
HEY, DONGX Y, KANGG L,et al .Asymptotic soft filter pruning for deep convolutional neural networks[J]. IEEE Transactions on Cybernetics,2020,50(8):3594-3604.
[42]
WANGJ L, JIANGT, CUIZ Y,et al .Filter pruning with a feature map entropy importance criterion for convolution neural networks compressing[J]. Neurocomputing,2021,461(C):41-54.
[43]
CANHT N, DINHK Q, JEONB .Decomposition-based multiscale compressed sensing[C]//2018 International Workshop on Advanced Image Technology (IWAIT). Chiang Mai,Thailand. IEEE,2018:1-4.
[44]
HUANH, LIP C, ZOUN,et al .End-to-end super-resolution for remote-sensing images using an improved multi-scale residual network[J].Remote Sensing,2021,13(4):666.
[45]
GAOC, ZHOUR G, LIX .Quantum color image scaling based on bilinear interpolation[J].Chinese Physics B,2023,32(5):050303.
[46]
WANGZ F, WANGZ H, ZENGC Y,et al .High-quality image compressed sensing and reconstruction with multi-scale dilated convolutional neural network[J].Circuits,Systems,and Signal Processing, 2023, 42(3): 1593-1616.
[47]
HOUQ B, ZHOUD Q, FENGJ S .Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville,TN,USA. IEEE,2021:13708-13717.
[48]
SRINIVASANN. A computational perspective on visual attention [J]. Current Science, 2013, 104(11): 1560-1561.
[49]
吴立帅 .深度神经网络中的结构化模型压缩算法研究与应用[D].成都:电子科技大学,2020.
[50]
WUL S .Research and Application of Structured Model Compression Algorithm in Deep Neural Network[D]. Chengdu:University of Electronic Science and Technology of China,2020.(in Chinese)
[51]
AGUSTSSONE, TIMOFTER .NTIRE 2017 challenge on single image super-resolution:dataset and study[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Honolulu,HI,USA. IEEE,2017:1122-1131.
[52]
YOUD, XIEJ F, ZHANGJ .ISTA-NET:flexible deep unfolding network for compressive sensing[C]//2021 IEEE International Conference on Multimedia and Expo (ICME).Shenzhen,China. IEEE,2021:1-6.