基于残差特征聚合的图像压缩感知注意力神经网络

doi:10.11896/jsjkx.211200215

摘要/Abstract

摘要： 基于深度学习的图像压缩感知方法由于其具有强大的学习能力和快速的处理速度受到了广泛关注。随着卷积神经网络深度的增加,现有使用神经网络的图像重构方法未充分利用网络中的残差特征。为了解决这一问题,通过联合优化采样和逆重构过程,提出了一个基于残差特征聚合的图像压缩感知注意力神经网络框架。首先,构建了块压缩感知采样子网络和初始重构子网络,以自适应地学习测量矩阵并生成初步的重构图像。然后引入残差学习与空间注意力机制,构建残差特征聚合注意力重构子网络使残差特征更加集中于关键的空间内容,以进一步提高重构图像质量。实验结果表明,所提网络在重构时间相当的情况下优于现有的图像压缩感知重构算法,获得了更加优良的图像压缩感知重构质量。具体地,在采样率为0.10的情况下,使用11幅图像进行测试,与其他基于深度学习的方法相比,其平均峰值信噪比提高了0.34~6.18 dB。

关键词: 图像压缩感知, 卷积神经网络, 特征聚合, 注意力

Abstract: Deep learning-based image compressive sensing has received extensive attention due to its powerful learning ability and fast processing speed.With the increase in the depth of convolutional neural networks,the existing image reconstruction methods using neural networks do not fully utilize the residual features in the network.In order to solve this problem,this paper proposes a compressed sensing attention neural network framework based on residual feature aggregation(RFA²CSNet)by jointly optimizing the sampling and inverse reconstruction processes.First,the block compressed sensing sampling sub-network and the initial reconstruction sub-network are constructed to adaptively learn the measurement matrix and generate the initial reconstruction image.Then the residual learning and spatial attention mechanisms are introduced to construct the residual feature aggregation attention reconstruction sub-network to make the residual feature more focused on the key spatial content,so as to further improve the reconstructed image quality.Experimental results show that the proposed network is superior to the existing image compressed sensing reconstruction algorithm in the case of comparable reconstruction time,and obtains better image compressive sensing reconstruction quality.Specifically,using 11 images for testing with a sampling rate of 0.10,the average peak signal-to-noise ratio increases by 0.34~6.18 dB compared with other deep learning-based methods.

Key words: Image compressed sensing, Convolution neural network, Feature aggregation, Attention

中图分类号:

TP391

王振彪, 覃亚丽, 王荣芳, 郑欢. 基于残差特征聚合的图像压缩感知注意力神经网络[J]. 计算机科学, 2023, 50(4): 117-124. https://doi.org/10.11896/jsjkx.211200215

WANG Zhenbiao, QIN Yali, WANG Rongfang, ZHENG Huan. Image Compressed Sensing Attention Neural Network Based on Residual Feature Aggregation[J]. Computer Science, 2023, 50(4): 117-124. https://doi.org/10.11896/jsjkx.211200215

参考文献

[1]DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory.2006,52(4):1289-1306.
[2]CANDES E J,JUSTIN R 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.
[3]CANDES E J,WAKIN M B.An introduction to compressivesampling[J].IEEE Signal Processing Magazine,2008,25(2):21-30.
[4]ROMBERG J.Imaging via compressive sampling[J].IEEE Signal Processing Magazine,2008,25(2):14-20.
[5]DUARTE M F,DAVENPORT M A,TAKHAR D,et al.Single-pixel imaging via compressive sampling[J].IEEE Signal Proces-sing Magazine,2008,25(2):83-91.
[6]EDGAR M P,SUN M J,GIBSON G M,et al.Real-time 3D videoutilizing a compressed sensing time-of-flight single-pixel camera[C]//Optical Trapping and Optical Micromanipulation XIII.2016:9921-9922.
[7]YAN Y,HUIBIN L,ZONGBEN X,et al.Deep ADMM-Net for compressive sensing MRI[C]//Advances in Neural Information Processing Systems(NIPS).2016:10-18.
[8]LIU Y X,YUAN X,SUO J L,et al.Rank minimization forsnapshot compressive imaging[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(12):2990-3006.
[9]YIN W,OSHER S,GOLDFARB D,et al.Bregman iterative algorithms forl₁-minimization with applications to compressed sensing[J].Siam Journal On Imaging Sciences,2008,1(1):143-168.
[10]LI Y,DAI W,ZOU J,et al.Structured sparse representation with union of data-driven linear and multilinear subspaces model for compressive video sampling[J].IEEE Transactions on Signal Processing,2017,65(19):5062-5077.
[11]LIAN Q S,CHEN S Z.Image reconstruction for compressedsensing based on the combined sparse image representation[J].Acta Automatica Sinica,2010,36(3):385-391.
[12]SHEN Y F,LI J T,ZHU Z M,et al.Image reconstruction algorithm of compressed sensing based on nonlocal similarity model[J].Acta Automatica Sinica,2015,41(2):261-272.
[13]GAN L.Block compressed sensing of natural images[C]//International Conference on Digital Signal Processing.2007:403-406.
[14]MUN S,FOWLER J E.Block compressed sensing of imagesusing directional transforms[C]//IEEE International Confe-rence on Image Processing(ICIP).2009:3021-3024.
[15]FOWLER J E,MUN S,TRAMEL E W.Block-based com-pressed sensing of images and video[J].Foundations and Trends in Signal Processing,2012,4(4):297-416.
[16]YING Y,WANG B,ZHANG L.Saliency-based compressivesampling for image signals[J].IEEE Signal Processing Letters,2010,17(11):973-976.
[17]PAN Z M,QIN Y L,ZHENG H,et al.Block compressed sen-sing image reconstruction via deep learning with smoothed projected Landweber[J].Journal of Electronic Imaging,2021,30(4):041402.
[18]ZHOU S,HE Y,LIU Y,et al.Multi-channel deep networks for block-based image compressive sensing[J].IEEE Transactions on Multimedia,2020,23:2627-2640.
[19]ZHANG X,LIAN Q,YANG Y,et al.A deep unrolling network inspired by total variation for compressed sensing MRI[J/OL].https://doi.org/10.1016/j.dsp.2020.102856.
[20]KULKARNI K,LOHIT S,TURAGA P,et al.ReconNet:no-n-iterative reconstruction of images from compressively sensed measurements[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.2016:449-458.
[21]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.
[22]HE K,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:770-778.
[23]ZHANG J,GHANEM B.ISTA-Net:Interpretable optimization-inspired deep network for image compressive sensing[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition.2018:828-1837.
[24]LI N Y,ZHOU C C.AMPA-Net:Optimization-Inspired Attention Neural Network for Deep Compressed Sensing[C]//2020 IEEE 20th International Conference on Communication Technology.2020:1338-1344.
[25]SHI W Z,JIANG F,ZHANG S P,et al.Deep networks for compressed image sensing[C]//IEEE International Conference on Computer Vision and Pattern Recognition.2016.
[26]SHI W Z,JIANG F,LIU S H,et al.Scalable convolutional neural network for image compressed sensing[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition.2019:12290-12299.
[27]SHI W Z,JIANG F,LIU S H,et al.Image compressed sensing using convolutional neural network[J].IEEE Transactions on Image Processing,2020,29:375-388.
[28]SUN Y J,CHEN J,LIU Q,et al.Dual-Path Attention Network for Compressed Sensing Image Reconstruction[J].IEEE Transac-tions on Image Processing,2020,29:9482-9495.
[29]CHEN S S,SAUNDERSD.Atomic decomposition by basis pursuit[J].SIAM review,2001,43(1):129-159.
[30]YANG M,HOOG F D.Orthogonal matching pursuit withthresholding and its application in compressive sensing[J].IEEE Transactions on Signal Processing,2015,63(20):5479-5486.
[31]METZLER C A,MALEKI A,BARANIUK R G.From denoising to compressed sensing[J].IEEE Transactions on Information Theory,2016,62(9):5117-5144.
[32]LIU J,ZHANG W,TANG Y,et al.Residual feature aggregation network for image super-resolution[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition.2020:2356-2365.
[33]ZHU X,CHENG D Z,ZHANG Z,et al.An Empirical Study of Spatial Attention Mechanisms in Deep Networks[C]//IEEE International Conference on Computer Vision and Pattern Recognition.2019.
[34]ARBELAEZP,MAIRE M,FOWLKES C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(5):898-916.
[35]KINGMA D,BA J.Adam:A method for stochastic optimization[C]//International Conference for Learning Representations.2015.
[36]LIAN Q S,FU L P,CHEN S Z,et al.A compressed sensing algorithm based on multiscale residual reconstruction network[J].Acta Automatica Sinica,2019,45(11):2082-2091.
[37]LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:common objects in context[C]//Computer Vision-ECCV 2014 Lecture Notes in Computer Science.2014:740-755.

相关文章 15

[1]	邵云飞, 宋友, 王宝会. 基于社交网络图节点度的神经网络个性化传播算法研究 Study on Degree of Node Based Personalized Propagation of Neural Predictions forSocial Networks 计算机科学, 2023, 50(4): 16-21. https://doi.org/10.11896/jsjkx.220300274
[2]	韩雪明, 贾彩燕, 李轩涯, 张鹏飞. 传播树结构结点及路径双注意力谣言检测模型 Dual-attention Network Model on Propagation Tree Structures for Rumor Detection 计算机科学, 2023, 50(4): 22-31. https://doi.org/10.11896/jsjkx.220200037
[3]	尹恒, 张凡, 李天瑞. 基于多邻接图与多头注意力机制的短期交通流量预测 Short-time Traffic Flow Forecasting Based on Multi-adjacent Graph and Multi-head Attention Mechanism 计算机科学, 2023, 50(4): 40-46. https://doi.org/10.11896/jsjkx.220200079
[4]	雒晓辉, 吴云, 王晨星, 余文婷. 基于用户长短期偏好的序列推荐模型 Sequential Recommendation Model Based on User’s Long and Short Term Preference 计算机科学, 2023, 50(4): 47-55. https://doi.org/10.11896/jsjkx.220100264
[5]	白雪飞, 靳智超, 王文剑, 马亚楠. 融合边缘增强与多尺度注意力的皮肤病变分割 Skin Lesion Segmentation Combining Boundary Enhancement and Multi-scale Attention 计算机科学, 2023, 50(4): 96-102. https://doi.org/10.11896/jsjkx.220300054
[6]	杨晓宇, 李超, 陈舜尧, 李浩亮, 殷光强. 基于Transformer的图文跨模态检索算法 Text-Image Cross-modal Retrieval Based on Transformer 计算机科学, 2023, 50(4): 141-148. https://doi.org/10.11896/jsjkx.220100083
[7]	王娅丽, 张凡, 余增, 李天瑞. 基于交互注意力和图卷积网络的方面级情感分析 Aspect-level Sentiment Classification Based on Interactive Attention and Graph Convolutional Network 计算机科学, 2023, 50(4): 196-203. https://doi.org/10.11896/jsjkx.220100105
[8]	贺超, 陈进杰, 金钊, 雷印杰. 基于多模态时-频特征融合的信号调制格式识别方法 Automatic Modulation Recognition Method Based on Multimodal Time-Frequency Feature Fusion 计算机科学, 2023, 50(4): 226-232. https://doi.org/10.11896/jsjkx.220600242
[9]	于兴崭, 芦天亮, 杜彦辉, 王曦锐, 杨成. 基于合成图像和Xception改进模型的安卓恶意家族分类方法 Android Malware Family Classification Method Based on Synthetic Image and Xception Improved Model 计算机科学, 2023, 50(4): 351-358. https://doi.org/10.11896/jsjkx.220300200
[10]	曹晨阳, 杨晓东, 段鹏松. WiDoor:一种近距离非接触式身份识别方法 WiDoor:Close-range Contactless Human Identification Approach 计算机科学, 2023, 50(4): 388-396. https://doi.org/10.11896/jsjkx.220300278
[11]	李帅, 徐彬, 韩祎珂, 廖同鑫. SS-GCN:情感增强和句法增强的方面级情感分析模型 SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement 计算机科学, 2023, 50(3): 3-11. https://doi.org/10.11896/jsjkx.220700238
[12]	陈富强, 寇嘉敏, 苏利敏, 李克. 基于图神经网络的多信息优化实体对齐模型 Multi-information Optimized Entity Alignment Model Based on Graph Neural Network 计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242
[13]	周明强, 代开浪, 吴全旺, 朱庆生. 异构信息网络的注意力感知多通道图卷积评分预测模型 Attention-aware Multi-channel Graph Convolutional Rating Prediction Model for Heterogeneous Information Networks 计算机科学, 2023, 50(3): 129-138. https://doi.org/10.11896/jsjkx.220300004
[14]	王晓飞, 樊学强, 李章维. 基于迁移学习和多视图特征融合提高RNA碱基相互作用预测 Improving RNA Base Interactions Prediction Based on Transfer Learning and Multi-view Feature Fusion 计算机科学, 2023, 50(3): 164-172. https://doi.org/10.11896/jsjkx.211200186
[15]	董永峰, 黄港, 薛婉若, 李林昊. 融合IRT的图注意力深度知识追踪模型 Graph Attention Deep Knowledge Tracing Model Integrated with IRT 计算机科学, 2023, 50(3): 173-180. https://doi.org/10.11896/jsjkx.211200134

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed