The Library
High-order paired-ASPP for deep semantic segmentation networks
Tools
Sun, Xin, Zhang, Yu, Chen, Changrui, Xie, Sihang and Dong, Junyu (2023) High-order paired-ASPP for deep semantic segmentation networks. Information Sciences, 646 . 119364. doi:10.1016/j.ins.2023.119364 ISSN 0020-0255.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: http://doi.org/10.1016/j.ins.2023.119364
Abstract
Current semantic segmentation models only exploit first-order information, while rarely exploring high-order semantics. However, traditional first-order statistics are insufficient to support a solid unanimous representation. In this paper, we propose High-Order Paired-ASPP (Atrous Spatial Pyramid Pooling) Network to exploit high-order statistics from various feature levels. The network first introduces a High-Order Representation module to extract the contextual high-order information from all stages of the backbone. They can provide more semantic clues and discriminative information than the first-order ones. Besides, a Paired-ASPP module is proposed to embed high-order statistics of the early stages into the last stage. It can further preserve the boundary-related and spatial context in the low-level features for final prediction. Our experiments show that the high-order semantics significantly boost the performance on confusing objects. Our method achieves competitive performance without bells and whistles on three benchmarks, i.e., Cityscapes, ADE20K and Pascal-Context.
Item Type: | Journal Article | ||||||||
---|---|---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||||
Journal or Publication Title: | Information Sciences | ||||||||
Publisher: | Elsevier | ||||||||
ISSN: | 0020-0255 | ||||||||
Official Date: | October 2023 | ||||||||
Dates: |
|
||||||||
Volume: | 646 | ||||||||
Article Number: | 119364 | ||||||||
DOI: | 10.1016/j.ins.2023.119364 | ||||||||
Status: | Peer Reviewed | ||||||||
Publication Status: | Published | ||||||||
Access rights to Published version: | Restricted or Subscription Access |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |