基于双重注意力特征增强网络的语义分割方法  

Dual Attention Based Feature Enhanced Networks for Semantic Segmentation

作　　者：赵芮 于晓艳[1] 荣宪伟[1] 

机构地区：[1]哈尔滨师范大学,黑龙江 哈尔滨

出　　处：《计算机科学与应用》2020年第11期1944-1951,共8页Computer Science and Application

摘　　要：语意分割作为计算机视觉领域的研究热点之一,在地理信息系统、医疗影像分析和机器人等领域有广泛应用。然而现有的语义分割方法主要面临两个挑战,即类内不一致和类间难区分问题。为此,我们提出了一种基于双重注意力特征增强网络的方法来实现语义分割。该方法采用位置注意力模块与通道注意力模块来获取丰富的空间信息与上下文信息,并且在网络末端添加金字塔池化模块来聚合不同区域的上下文信息,提高网络捕获全局信息的能力。最终在标准数据集上的实验结果验证了本文方法的有效性。As one of the research hotspots in the field of computer vision, semantic segmentation has been widely applied in various fields such as geographic information systems, medical image analysis and robotics. However, contemporary semantic segmentation tasks generally face two challenges, namely intra-class inconsistency problem and inter-class indistinction problem. To this end, we solve the semantic segmentation by proposing Dual Attention based Feature Enhanced Networks. In this method, the position attention module and channel attention module are used to obtain rich spatial and context information, and the pyramid pooling module is added at the end of the network to aggregate the context information of different regions, which could improve the capability of the networks to capture global information. Finally, the experimental results on the standard dataset demonstrate the effectiveness of the proposed method.

关 键 词：语义分割 双重注意力特征增强网络 位置注意力模块 通道注意力模块 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]