GFFNet: Global Feature Fusion Network for Semantic Segmentation of Large-Scale Remote Sensing Images

doi:10.1109/JSTARS.2024.3359656

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 遥感图像处理团队

	GFFNet: Global Feature Fusion Network for Semantic Segmentation of Large-Scale Remote Sensing Images
	Cao, Yong 1,2; Huo, Chunlei 1,2; Xiang, Shiming 1,2; Pan, Chunhong 1,2
刊名	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2024
卷号	17 页码:4222-4234
关键词	Cross feature fusion (CFF) global context learning group transformer semantic segmentation
ISSN号	1939-1404
DOI	10.1109/JSTARS.2024.3359656
通讯作者	Huo, Chunlei(clhuo@nlpr.ia.ac.cn)
英文摘要	Semantic segmentation plays a pivotal role in interpreting high-resolution remote sensing images (RSIs), where contextual information is essential for achieving accurate segmentation. Despite the common practice of partitioning large RSIs into smaller patches for deep model input, existing methods often rely on adaptations from natural image semantic segmentation techniques, limiting their contextual scope to individual images. To address this limitation and harness a broader range of contextual information from original large-scale RSIs, this study introduces a global feature fusion network (GFFNet). GFFNet employs a novel approach by incorporating a group transformer structure alternated with group convolution, forming a lightweight global context learning branch. This design facilitates the extraction of global contextual features from the large-scale RSIs. In addition, we propose a cross feature fusion module that seamlessly integrates local features obtained from the convolutional network with the global contextual features. GFFNet serves as a versatile plugin for existing RSI semantic segmentation models, particularly beneficial when the target dataset involves cropping. This integration enhances the model's performance, especially in terms of segmenting large-scale objects. Experimental results on the ISPRS and GID-15 datasets validate the effectiveness of GFFNet in improving segmentation capabilities for large-scale objects in RSIs.
资助项目	National Key Research and Development Program of China
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001165247100005
资助机构	National Key Research and Development Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/57962]
专题	自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者	Huo, Chunlei
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Key Lab Multimodal Artificial Intelligence Sy, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Cao, Yong,Huo, Chunlei,Xiang, Shiming,et al. GFFNet: Global Feature Fusion Network for Semantic Segmentation of Large-Scale Remote Sensing Images[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2024,17:4222-4234.
APA	Cao, Yong,Huo, Chunlei,Xiang, Shiming,&Pan, Chunhong.(2024).GFFNet: Global Feature Fusion Network for Semantic Segmentation of Large-Scale Remote Sensing Images.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,17,4222-4234.
MLA	Cao, Yong,et al."GFFNet: Global Feature Fusion Network for Semantic Segmentation of Large-Scale Remote Sensing Images".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17(2024):4222-4234.