TY - JOUR
T1 - Cascaded Hierarchical Atrous Spatial Pyramid Pooling Module for Semantic Segmentation
AU - Lian, Xuhang
AU - Pang, Yanwei
AU - Han, Jungong
AU - Pan, Jing
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China (Grant No. 61632018 ) and the National Key R&D Program of China (Grant Nos. 2018AAA0102800 and 2018AAA0102802).
Publisher Copyright:
© 2020
PY - 2021/2/1
Y1 - 2021/2/1
N2 - 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.
AB - 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.
KW - Atrous convolution
KW - Atrous spatial pyramid pooling(ASPP)
KW - Cascaded module
KW - Hierarchical pyramid pooling
KW - Semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85090594418&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2020.107622
DO - 10.1016/j.patcog.2020.107622
M3 - Article
SN - 0031-3203
VL - 110
JO - Pattern Recognition
JF - Pattern Recognition
M1 - 107622
ER -