干旱区生态环境知识资源中心(Arid): Multi-Resolution Supervision Network with an Adaptive Weighted Loss for Desert Segmentation

Arid

DOI	10.3390/rs13112054
	Multi-Resolution Supervision Network with an Adaptive Weighted Loss for Desert Segmentation
	Wang, Lexuan; Weng, Liguo; Xia, Min; Liu, Jia; Lin, Haifeng
通讯作者	Weng, LG (corresponding author), Nanjing Univ Informat Sci & Technol, Jiangsu Collaborat Innovat Ctr Atmospher Environm, Nanjing 210044, Peoples R China.
来源期刊	REMOTE SENSING
EISSN	2072-4292
出版年	2021
卷号	13 期号:11
英文摘要	Desert segmentation of remote sensing images is the basis of analysis of desert area. Desert images are usually characterized by large image size, large-scale change, and irregular location distribution of surface objects. The multi-scale fusion method is widely used in the existing deep learning segmentation models to solve the above problems. Based on the idea of multi-scale feature extraction, this paper took the segmentation results of each scale as an independent optimization task and proposed a multi-resolution supervision network (MrsSeg) to further improve the desert segmentation result. Due to the different optimization difficulty of each branch task, we also proposed an auxiliary adaptive weighted loss function (AWL) to automatically optimize the training process. MrsSeg first used a lightweight backbone to extract different-resolution features, then adopted a multi-resolution fusion module to fuse the local information and global information, and finally, a multi-level fusion decoder was used to aggregate and merge the features at different levels to get the desert segmentation result. In this method, each branch loss was treated as an independent task, AWL was proposed to calculate and adjust the weight of each branch. By giving priority to the easy tasks, the improved loss function could effectively improve the convergence speed of the model and the desert segmentation result. The experimental results showed that MrsSeg-AWL effectively improved the learning ability of the model and has faster convergence speed, lower parameter complexity, and more accurate segmentation results.
英文关键词	multi-resolution supervision adaptive weighted loss multi-scale fusion deep learning
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000660615900001
WOS关键词	MU US DESERT ; SEMANTIC SEGMENTATION ; FEATURE FUSION ; LAND ; DESERTIFICATION
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
来源机构	南京信息工程大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/351533
作者单位	[Wang, Lexuan; Weng, Liguo; Xia, Min; Liu, Jia] Nanjing Univ Informat Sci & Technol, Jiangsu Collaborat Innovat Ctr Atmospher Environm, Nanjing 210044, Peoples R China; [Lin, Haifeng] Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Peoples R China
推荐引用方式 GB/T 7714	Wang, Lexuan,Weng, Liguo,Xia, Min,et al. Multi-Resolution Supervision Network with an Adaptive Weighted Loss for Desert Segmentation[J]. 南京信息工程大学,2021,13(11).
APA	Wang, Lexuan,Weng, Liguo,Xia, Min,Liu, Jia,&Lin, Haifeng.(2021).Multi-Resolution Supervision Network with an Adaptive Weighted Loss for Desert Segmentation.REMOTE SENSING,13(11).
MLA	Wang, Lexuan,et al."Multi-Resolution Supervision Network with an Adaptive Weighted Loss for Desert Segmentation".REMOTE SENSING 13.11(2021).