SIA OpenIR  > 数字工厂研究室
Efficient Attention Pyramid Network for Semantic Segmentation
Yang QR(杨琦瑞)1,2,3; Ku T(库涛)1,2; Hu KY(胡琨元)1,2
Department数字工厂研究室
Source PublicationIEEE Access
ISSN2169-3536
2021
Volume9Pages:18867-18875
Indexed BySCI ; EI
EI Accession number20210609895426
WOS IDWOS:000619303100001
Contribution Rank1
Funding OrganizationNational Key Research and Development Program of China under Grant 2019YFB17050003, Grant 2018YFB1308801, and Grant 2017YFB0306401 ; Consulting Research Project of the Chinese Academy of Engineering under Grant 2019-XZ-7.
KeywordSemantic segmentation attention mechanism spatial pyramid PASCAL VOC 2012 Cityscapes
Abstract

Semantic segmentation is a task that covers most of the perception needs of intelligent vehicles in an unified way. Recent studies witnessed that attention mechanisms achieve impressive performance in computer vision task. Current attention mechanisms based segmentation methods differ with each other in position and form of the attention mechanism, and perform differently in practice. This paper firstly introduces the effectiveness of multi-scale context features and attention mechanisms in segmentation tasks. We find that multi-scale and channel attention can play a vital role in constructing effective context features. Based on this analysis, this paper proposes an efficient attention pyramid network (EAPNet) for semantic segmentation. Specifically, to efficient handle the problem of segmenting objects at multiple scales, we design efficient channel attention pyramid (ECAP) which employ atrous convolution with channel attention in cascade or in parallel to capture multi-scale context by using multiple atrous rates. Furthermore, we propose a residual attention fusion block (RAFB), whose purpose is to simultaneously focus on meaningful low-level feature maps and spatial location information. At the same time, we will explore different channel attention modules and spatial attention modules, and describe their impact on network performance. We empirically evaluate our EAPNet on two semantic segmentation datasets, including PASCAL VOC 2012 and Cityscapes datasets. Experimental results show that without MS COCO pre-training and any post-processing, EAPNet achieved 81.7% mIoU on the PASCAL VOC 2012 validation set. With deeplabv3+ as the benchmark, EAPNet improve the model performance of more than 1.50% mIoU.

Language英语
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Funding ProjectNational Key Research and Development Program of China[2019YFB17050003] ; National Key Research and Development Program of China[2018YFB1308801] ; National Key Research and Development Program of China[2017YFB0306401] ; Consulting Research Project of the Chinese Academy of Engineering[2019-XZ-7]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28337
Collection数字工厂研究室
Corresponding AuthorYang QR(杨琦瑞)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.School of Computer and Control, University of Chinese Academy of Sciences, Beijing 100049, China
Recommended Citation
GB/T 7714
Yang QR,Ku T,Hu KY. Efficient Attention Pyramid Network for Semantic Segmentation[J]. IEEE Access,2021,9:18867-18875.
APA Yang QR,Ku T,&Hu KY.(2021).Efficient Attention Pyramid Network for Semantic Segmentation.IEEE Access,9,18867-18875.
MLA Yang QR,et al."Efficient Attention Pyramid Network for Semantic Segmentation".IEEE Access 9(2021):18867-18875.
Files in This Item:
File Name/Size DocType Version Access License
Efficient Attention (1727KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang QR(杨琦瑞)]'s Articles
[Ku T(库涛)]'s Articles
[Hu KY(胡琨元)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang QR(杨琦瑞)]'s Articles
[Ku T(库涛)]'s Articles
[Hu KY(胡琨元)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang QR(杨琦瑞)]'s Articles
[Ku T(库涛)]'s Articles
[Hu KY(胡琨元)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Efficient Attention Pyramid Network for Semantic Segmentation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.