Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation

PATTERN RECOGNITION

卷:110

Article

Lian, Xuhang¹  Pang, Yanwei¹  Han, Jungong²  Pan, Jing^1,3 

[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China

[2] Aberystwyth Univ, Dept Comp Sci, Aberystwyth SY23 3DB, Dyfed, Wales

[3] Tianjin Univ Technol & Educ, Sch Elect Engn, Tianijn 300222, Peoples R China

关键词: Semantic segmentation;    Atrous convolution;    Atrous spatial pyramid pooling(ASPP);    Hierarchical pyramid pooling;    Cascaded module;   

DOI  :  10.1016/j.patcog.2020.107622

来源: Elsevier

【 摘 要 】

Atrous Spatial Pyramid Pooling (ASPP) is a module that can collect semantic information distributed in different scopes. However, because of the limited number of sampling ranges of ASPP, much valuable global features and contextual information cannot be sufficiently sampled, which degrades the repre-sentation ability of the segmentation network. Besides, due to the sparse distribution of the effective sampling points in the atrous convolution kernels of ASPP, large amount of local detail characteristics are easily discarded. To overcome the above two problems, a new Cascaded Hierarchical Atrous Pyramid Pooling (CHASPP) module, consisting of two cascaded components, is proposed. Each component is a hierarchical pyramid pooling structure containing two layers of atrous convolutions with the aim to densify the sampling distribution. On the foundation of such a hierarchical structure, another same structure is appended to form a cascaded module which can further enlarge the diversity of sampling ranges. Based on this cascaded module, not only rich local detail characteristics can be comprehensively presented, but also important global contextual information can be effectively exploited to improve the prediction accuracy. To demonstrate the performance of our CHASPP module, experiments on the benchmarks PASCAL VOC 2012 and Cityscape are conducted. (c) 2020 Elsevier Ltd. All rights reserved.

【 授权许可】

Free