典型文献
Real-Time Semantic Segmentation via an Efficient Multi-Column Network
文献摘要：
Existing semantic segmentation networks based on the multi-column structure can hardly satisfy the efficiency and precision requirements simultaneously due to their shallow spatial branches.In this paper,we propose a new efficient multi-column network termed as LadderNet to address this problem.Our LadderNet includes two branches where the spatial branch generates high-resolution output feature map and the context branch encodes accurate semantic information.In particular,we first propose a channel attention fusion block and a global context module to enhance the information encoding ability of the context branch.Subsequently,a new branch fusion method,i.e.,fusing some middle feature maps of the context branch into the spatial branch,is developed to improve the depth of the spatial branch.Meanwhile,we design a feature fusing module to enhance the fusion quality of these two branches,leading to a more efficient network.We compare our model with other state-of-the-arts on PASCAL VOC 2012 and Cityscapes benchmarks.Experimental results demonstrate that,compared with other state-of-the-art methods,our LadderNet can achieve average 1.25％mIoU improvement with comparable or less computation.
文献关键词：
中图分类号：
作者姓名：
Cheng-Li Peng;Jia-Yi Ma
作者机构：
Electronic Information School,Wuhan University,Wuhan 430072,China
文献出处：
引用格式：
[1]Cheng-Li Peng;Jia-Yi Ma-.Real-Time Semantic Segmentation via an Efficient Multi-Column Network)[J].计算机科学技术学报（英文版）,2022(06):1478-1491
A类：
LadderNet
B类：
Real,Time,Semantic,Segmentation,via,Efficient,Multi,Column,Network,Existing,semantic,segmentation,networks,multi,column,structure,can,hardly,satisfy,efficiency,precision,requirements,simultaneously,due,their,shallow,spatial,branches,In,this,paper,we,propose,new,efficient,termed,address,problem,Our,includes,where,generates,high,resolution,output,feature,context,encodes,accurate,information,particular,first,channel,attention,fusion,block,global,module,enhance,encoding,ability,Subsequently,fusing,some,middle,maps,into,developed,depth,Meanwhile,design,quality,these,leading,more,We,our,model,other,state,arts,PASCAL,VOC,Cityscapes,benchmarks,Experimental,results,demonstrate,that,compared,methods,achieve,average,mIoU,improvement,comparable,less,computation
AB值：
0.581358
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。
