A Deeply Supervised Attentive High-Resolution Network for Change Detection in Remote Sensing Images

doi:10.3390/rs15010045

	A Deeply Supervised Attentive High-Resolution Network for Change Detection in Remote Sensing Images
	Wu, Jinming 1,2; Xie, Chunhui1,3 ; Zhang, Zuxi 1,2; Zhu, Yongxin 1
	2023
发表期刊	REMOTE SENSING (IF:4.2[JCR-2023],4.9[5-Year])
EISSN	2072-4292
卷号	15 期号:1
发表状态	已发表
DOI	10.3390/rs15010045
摘要	Change detection (CD) is a crucial task in remote sensing (RS) to distinguish surface changes from bitemporal images. Recently, deep learning (DL) based methods have achieved remarkable success for CD. However, the existing methods lack robustness to various kinds of changes in RS images, which suffered from problems of feature misalignment and inefficient supervision. In this paper, a deeply supervised attentive high-resolution network (DSAHRNet) is proposed for remote sensing image change detection. First, we design a spatial-channel attention module to decode change information from bitemporal features. The attention module is able to model spatial-wise and channel-wise contexts. Second, to reduce feature misalignment, the extracted features are refined by stacked convolutional blocks in parallel. Finally, a novel deeply supervised module is introduced to generate more discriminative features. Extensive experimental results on three challenging benchmark datasets demonstrate that the proposed DSAHRNet outperforms other state-of-the-art methods, and achieves a great trade-off between performance and complexity.
关键词	change detection convolutional neural network feature fusion metric learning attention mechanism
URL	查看原文
收录类别	SCI ; EI ; SCOPUS
语种	英语
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000908503400001
出版者	MDPI
EI入藏号	20230213363996
EI主题词	Change detection
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 601.1 Mechanical Devices ; 716.1 Information Theory and Signal Processing ; 971 Social Sciences
原始文献类型	Journal article (JA)
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/272827
专题	信息科学与技术学院_硕士生
通讯作者	Zhu, Yongxin
作者单位	1.Chinese Acad Sci, Shanghai Adv Res Inst, Shanghai 201210, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
推荐引用方式 GB/T 7714	Wu, Jinming,Xie, Chunhui,Zhang, Zuxi,et al. A Deeply Supervised Attentive High-Resolution Network for Change Detection in Remote Sensing Images[J]. REMOTE SENSING,2023,15(1).
APA	Wu, Jinming,Xie, Chunhui,Zhang, Zuxi,&Zhu, Yongxin.(2023).A Deeply Supervised Attentive High-Resolution Network for Change Detection in Remote Sensing Images.REMOTE SENSING,15(1).
MLA	Wu, Jinming,et al."A Deeply Supervised Attentive High-Resolution Network for Change Detection in Remote Sensing Images".REMOTE SENSING 15.1(2023).