Dual context prior and refined prediction for semantic segmentation

作     者：Long Chen Jiajie Liu Han Li Wujing Zhan Baoding Zhou Qingquan Li Long Chen;Jiajie Liu;Han Li;Wujing Zhan;Baoding Zhou;Qingquan Li

作者机构：School of Data and Computer ScienceSun Yat-sen UniversityGuangzhouChina Guangdong Key Laboratory of Urban InformaticsShenzhen UniversityShenzhenChina Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)Shenzhen UniversityShenzhenChina Civil and Transportation EngineeringShenzhen UniversityShenzhenChina 

出 版 物：《Geo-Spatial Information Science》 (地球空间信息科学学报（英文）)

年 卷 期：2021年第24卷第2期

页      面：228-240,I0004页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Deep learning semantic segmentation linear spatial propagation context information 

摘      要：Recently,the focus of semantic segmentation research has shifted to the aggregation of context prior and refined boundary.A typical network adopts context aggregation modules to extract rich semantic *** also utilizes top-down connection and skips connections for refining boundary *** it still remains disadvantage,an obvious fact is that the problem of false segmentation occurs as the object has very different *** fusion of weak semantic and low-level features leads to context prior *** tackle the issue,we propose a simple yet effective network,which integrates dual context prior and spatial propagation-dubbed *** extends two mainstreams of current segmentation researches:(1)Designing a dual context prior module,which pays attention to context prior again with a shortcut connection.(2)The network can inherently learn semantic aware affinity values for each pixel and refine the *** will present detailed comparisons,which perform on PASCAL VOC 2012 and *** result demonstrates the validation of our approach.