Circle-Net: An Unsupervised Lightweight-Attention Cyclic Network for Hyperspectral and Multispectral Image Fusion

doi:10.1109/JSTARS.2023.3271359

	Circle-Net: An Unsupervised Lightweight-Attention Cyclic Network for Hyperspectral and Multispectral Image Fusion
	Liu, Shuaiqi 3,4; Miao, Siyu 2; Liu, Siyuan 2; Li, Bing 4; Hu, Weiming 4; Zhang, Yu-Dong 1
刊名	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2023
卷号	16 页码:4499-4515
关键词	Attention mechanism deep learning (DL) hyperspectral images (HSIs) image fusion multispectral images (MSIs)
ISSN号	1939-1404
DOI	10.1109/JSTARS.2023.3271359
通讯作者	Miao, Siyu(siyumiao_hbu@163.com) ; Liu, Siyuan(syliu_hbu@163.com)
英文摘要	Hyperspectral image (HSI) and multispectral image (MSI) fusion has the potential to significantly improve the quality and usefulness of data, leading to better decision-making and a more complete understanding of the observed scene. For HSI and MSI fusion, capturing matched pairs of HSI and MSI images is challenging. This hampers the pretraining of neural-network-based HSI-MSI fusion methods and yields unsatisfactory fusion results. A lightweight-attention (LA) cyclic network (Circle-Net) without pretraining using labeled data is constructed and applied to HSI-MSI fusion to alleviate this issue. Circle-Net consists of a coordinate feature fusion (CFF) network and a dual-attention decoder (DAD) network. Multiscale features collected from the DAD network are fused by the CFF network to derive a high-resolution HSI. Specifically, in the DAD network, skip connections in the encoder-decoder network are replaced by LAs, while polarized attention is used to guarantee efficient transfer of features between the encoder and decoder. In comparison with other methods, the experimental performance shows the superiority of the Circle-Net in both visual and quantitative performance.
资助项目	National Natural Science Foundation of China[62172139] ; National Natural Science Foundation of China[U1936204] ; National Key RD Plan[2020AAA0106800] ; Natural Science Foundation of Hebei Province[F2022201055] ; China Postdoctoral[2022M713361] ; Science Research Project of Hebei Province[BJ2020030] ; Natural Science Interdisciplinary Research Program of Hebei University[DXK202102] ; Open Project Program of NLPR[202200007]
WOS关键词	RECONSTRUCTION ; FACTORIZATION
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:001010424300008
资助机构	National Natural Science Foundation of China ; National Key RD Plan ; Natural Science Foundation of Hebei Province ; China Postdoctoral ; Science Research Project of Hebei Province ; Natural Science Interdisciplinary Research Program of Hebei University ; Open Project Program of NLPR
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53492]
专题	中国科学院自动化研究所
通讯作者	Miao, Siyu; Liu, Siyuan
作者单位	1.Univ Leicester, Sch Comp & Math, Leicester LE1 7RH, England 2.Hebei Univ, Coll Elect & Informat Engn, Key Lab Digital Med Engn Hebei Prov, Baoding 071002, Peoples R China 3.Hebei Univ, Coll Elect & Informat Engn, Machine Vis Engn Res Ctr Hebei Prov, Baoding 071002, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu, Shuaiqi,Miao, Siyu,Liu, Siyuan,et al. Circle-Net: An Unsupervised Lightweight-Attention Cyclic Network for Hyperspectral and Multispectral Image Fusion[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2023,16:4499-4515.
APA	Liu, Shuaiqi,Miao, Siyu,Liu, Siyuan,Li, Bing,Hu, Weiming,&Zhang, Yu-Dong.(2023).Circle-Net: An Unsupervised Lightweight-Attention Cyclic Network for Hyperspectral and Multispectral Image Fusion.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,16,4499-4515.
MLA	Liu, Shuaiqi,et al."Circle-Net: An Unsupervised Lightweight-Attention Cyclic Network for Hyperspectral and Multispectral Image Fusion".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 16(2023):4499-4515.