Real-Time Semantic Segmentation via an Efficient Multi-Column Network  

作　　者：Cheng-Li Peng Jia-Yi Ma 彭程里;马佳义(Electronic Information School,Wuhan University,Wuhan 430072,China)

机构地区：[1]Electronic Information School,Wuhan University,Wuhan 430072,China

出　　处：《Journal of Computer Science & Technology》2022年第6期1478-1491,共14页计算机科学技术学报（英文版）

基　　金：the National Natural Science Foundation of China under Grant No.61773295。

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.

关 键 词：semantic segmentation real time multi-column network deep learning 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]