典型文献
Channel attention based wavelet cascaded network for image super-resolution
文献摘要：
Convolutional neural networks(CNNs)have shown great potential for image super-resolution(SR).However,most existing CNNs only reconstruct images in the spatial domain,resulting in in-sufficient high-frequency details of reconstructed images.To address this issue,a channel attention based wavelet cascaded network for image super-resolution(CWSR)is proposed.Specifically,a second-order channel attention(SOCA)mechanism is incorporated into the network,and the covar-iance matrix normalization is utilized to explore interdependencies between channel-wise features.Then,to boost the quality of residual features,the non-local module is adopted to further improve the global information integration ability of the network.Finally,taking the image loss in the spatial and wavelet domains into account,a dual-constrained loss function is proposed to optimize the net-work.Experimental results illustrate that CWSR outperforms several state-of-the-art methods in terms of both visual quality and quantitative metrics.
文献关键词：
中图分类号：
作者姓名：
CHEN Jian;HUANG Detian;HUANG Weiqin
作者机构：
College of Engineering,Huaqiao University,Quanzhou 362021,P.R.China;School of Information Science and Technology,Xiamen University Tan Kah Kee College,Zhangzhou 363105,P.R.China
文献出处：
引用格式：
[1]CHEN Jian;HUANG Detian;HUANG Weiqin-.Channel attention based wavelet cascaded network for image super-resolution)[J].高技术通讯（英文版）,2022(02):197-207
A类：
CWSR,covar,iance,interdependencies
B类：
Channel,attention,wavelet,cascaded,super,resolution,Convolutional,neural,networks,CNNs,have,shown,great,potential,However,most,existing,only,images,spatial,resulting,sufficient,high,frequency,details,reconstructed,To,address,this,issue,channel,proposed,Specifically,second,order,SOCA,mechanism,incorporated,into,matrix,normalization,utilized,explore,between,wise,features,Then,boost,quality,residual,local,module,adopted,further,improve,global,information,integration,ability,Finally,taking,loss,domains,account,constrained,function,optimize,Experimental,results,illustrate,that,outperforms,several,state,art,methods,terms,both,visual,quantitative,metrics
AB值：
0.559368
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
