高效二阶注意力对偶回归网络的超分辨率重建  

Super-Resolution Reconstruction of Efficient Second-Order Attention Dual Regression Network

作　　者：廉炜雯 吴斌[1,2] 张红英 李雪[1,2] LIAN Weiwen;WU Bin;ZHANG Hongying;LI Xue(School of Information Engineering,Southwest University of Science and Technology,Mianyang,Sichuan 621010,China;Robot Technology Used for Special Environment Key Laboratory of Sichuan Province,Mianyang,Sichuan 621010 China)

机构地区：[1]西南科技大学信息工程学院,四川绵阳621010 [2]特殊环境机器人技术四川省重点实验室,四川绵阳621010

出　　处：《计算机工程与应用》2022年第20期220-228,共9页Computer Engineering and Applications

基　　金：国家部委预研基金。

摘　　要：针对中间层通道特征相关性利用率低、低分辨率图像和高分辨率图像函数映射空间非线性的问题,提出了一种基于高效二阶注意力机制的对偶回归网络(ESADRNet)。该网络将重建任务分为两个回归网络:原始回归网络和对偶回归网络。原始回归网络采用FReLU为激活函数的下采样层对图像进行更高效的空间上下文特征提取;基于多级跳跃连接残差块(MLSCR)和高效二阶通道注意力模块(ESOCA)构成的多级跳跃连接残差注意力模块(MLSCRAG)、共享源跳跃连接(SSC)和亚像素卷积构建渐进式上采样网络,使网络专注于更具辨别性的特征表示,具有更强大的特征表达和特征相关学习能力;利用对偶回归网络约束映射空间,寻找最优重建函数。在Set5、Set14、BSD100和Urban109数据集上经过对比实验证明,该网络在客观定量指标和主观视觉方面均优于其他对比方法。Aiming at low channel feature correlation utilization in the middle layer and nonlinear mapping of low-resolution images and high-resolution images,a dual regression network based on an efficient second-order attention(ESADRNet)is proposed.The network divides the reconstruction task into two regression networks:the original regression network and the dual regression network.The original regression network firstly uses FReLU as the down-sampling layer of the activation function to extract more efficient spatial context features of the image.Meanwhile,the method based on the multi-level skip connection residual attention group(MLSCRAG)composed of the multi-level skip connection residual(MLSCR)and the efficient second-order channel attention(ESOCA)module and shared source connection(SSC)and sub-pixel convolution constructs a progressive up-sampling network,so that the network can focus on more discrimina-tive feature representation,and has more powerful feature expression and feature-related learning capabilities.Finally,the dual regression network is used to constrain the mapping space,and find the optimal reconstruction function.After com-parative experiments on the Set5,Set14,BSD100 and Urban109 datasets,it is proved that the network is superior to other methods in terms of objective quantitative indicators and subjective vision.

关 键 词：超分辨率重建 注意力机制 对偶回归网络 卷积神经网络 深度学习 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]