Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation

作者：

Highlights：

• A new hierarchical structure consisting of multiple levels of atrous convolution layers.

• A novel Cascaded Hierarchical Atrous Spatial Pyramid Pooling (CHASPP) network by cascading the hierarchical structures is constructed.

• Global features and context information is extensively collected to form a more reasonable and accurate prediction.

• The segmentation method outperforms the state of the arts.

摘要

•A new hierarchical structure consisting of multiple levels of atrous convolution layers.•A novel Cascaded Hierarchical Atrous Spatial Pyramid Pooling (CHASPP) network by cascading the hierarchical structures is constructed.•Global features and context information is extensively collected to form a more reasonable and accurate prediction.•The segmentation method outperforms the state of the arts.

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

论文评审过程：Received 14 February 2019, Revised 31 December 2019, Accepted 29 August 2020, Available online 5 September 2020, Version of Record 13 September 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107622