Cascaded Hierarchical Atrous Spatial Pyramid Pooling Module for Semantic Segmentation

Xuhang Lian, Yanwei Pang, Jungong Han, Jing Pan

Research output: Contribution to journalArticlepeer-review

88 Citations (Scopus)
503 Downloads (Pure)

Abstract

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 representation 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.
Original languageEnglish
Article number107622
JournalPattern Recognition
Volume110
Early online date05 Sept 2020
DOIs
Publication statusPublished - 01 Feb 2021

Keywords

  • Atrous convolution
  • Atrous spatial pyramid pooling(ASPP)
  • Cascaded module
  • Hierarchical pyramid pooling
  • Semantic segmentation

Fingerprint

Dive into the research topics of 'Cascaded Hierarchical Atrous Spatial Pyramid Pooling Module for Semantic Segmentation'. Together they form a unique fingerprint.

Cite this