Pooling Attention-based Encoder-Decoder Network for semantic segmentation

作     者：Xu, Haixia Huang, Yunjia Hancock, Edwin R. Wang, Shuailong Xuan, Qijun Zhou, Wei 

作者机构：Xiangtan Univ Coll Automat & Elect Informat Xiangtan 411105 Peoples R China Xiangtan Univ Coll Comp Sci Xiangtan 411105 Peoples R China Univ York Dept Comp Sci York YO10 5DD N Yorkshire England 

出 版 物：《COMPUTERS & ELECTRICAL ENGINEERING》 (计算机与电工)

年 卷 期：2021年第93卷

页      面：107260-107260页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：NSFC [U19A2083] Science and Technology Plan Project of Hunan Province, China [2016TP1020] open fund project of Hunan Provincial Key Laboratory of Intelligent Information Processing and Application for Hengyang normal university, China [IIPA20K04] 

主　　题：Semantic segmentation Encoder-Decoder Pooling attention module Channel Position 

摘      要：Aiming to the challenge of poor pixel-consistency in inter-category and pixel-similarity in inter-category, in this paper, we propose an Encoder-Decoder network for image semantic segmentation using pooling SE-ResNet attention module, called PAEDN. It is an effective of attention mechanism to get aggregated information. According to the principle of SE-ResNet, a collection of Average, Maximum and Stochastic global pooling, which concentrate on contoured, detailed, and generalized information in a certain semantic segmentation, form attention modules. Channel Pooling Attention Module (CPAM) and Position Pooling Attention Module (PPAM) are designed and integrated into the Encoder to extract discriminative features from input images, and the Decoder is developed through SE-ResNet attention module to fuse the feature map in high-resolution with that in low-resolution. Experimental evaluations performed on the data sets PASCAL and Cityscapes, show the proposed Encoder-Decoder with pooling attention module produces good pixel-consistency semantic label, achieves 15.1% improvement to FCN.