中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
MCAMamba: Multilevel Cross-Modal Attention-Guided State-Space Model for Multisource Remote Sensing Image Classification

文献类型：期刊论文

作者Dou, Mingyu3,4; Qiu, Shi3; Hu, Ming3; Qiao, Xiaozhen5; Ye, Huping1,6; Liao, Xiaohan1,6,7; Sun, Zhe2
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2025
卷号63页码:4707819
关键词Remote sensing Feature extraction Computational modeling Transformers Laser radar Computational efficiency Adaptation models Synthetic aperture radar Faces Computational complexity Attention mechanism hyperspectral image (HSI) light detection and ranging (LiDAR) multisource remote sensing classification state-space model (SSM) synthetic aperture radar (SAR)
ISSN号0196-2892
DOI10.1109/TGRS.2025.3618301
产权排序4
文献子类Article
英文摘要Effective fusion of multisource remote sensing data remains a fundamental challenge for Earth observation, as convolutional neural network (CNN) and transformer models suffer from limited receptive fields and high computational complexity. While state-space models (SSMs) like Mamba show promise in sequence modeling, they face three critical challenges in multisource remote sensing: insufficient spatial-spectral coordination, cross-modal heterogeneity, and inadequate multiscale feature integration. To address these limitations, this article proposes a multilevel cross-modal attention-guided Mamba (MCAMamba) framework for joint classification of hyperspectral images (HSI) and light detection and ranging (LiDAR)/synthetic aperture radar (SAR) data. MCAMamba introduces a novel three-stage feature fusion pipeline: 1) the feature extraction attention (FExt-Attention) module enhances spatial structure and spectral information through parallel spatial-channel attention (Cha-Attn) mechanisms; 2) the SSM-Attention module achieves deep cross-modal fusion by combining attention mechanisms with SSM for parametric interaction; and 3) the feature fusion attention (FFus-Attention) module performs adaptive multiscale feature integration through global context modeling and cascaded attention. This hierarchical design enables superior feature representation with enhanced computational efficiency. Experiments on four public benchmark datasets (Houston2013, Houston2018, Augsburg, and Berlin) show that MCAMamba achieves overall accuracy (OA) of 94.75%, 93.35%, 92.46%, and 79.18%. The code will be available at https://github.com/Dmygithub/MCAMamba
URL标识查看原文
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001604968000004
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://ir.igsnrr.ac.cn/handle/311030/217712]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Qiu, Shi; Sun, Zhe
作者单位1.Chinese Acad Sci, Civil Aviat Adm China, Key Lab Low Altitude Geog Informat & Air Route, Beijing 100101, Peoples R China;
2.Northwestern Polytech Univ, Sch Artificial Intelligence Opt & Elect iOPEN, Xian 710072, Peoples R China
3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, CAS, Key Lab Spectral Imaging Technol, Xian 710119, Peoples R China;
4.Univ Chinese Acad Sci, Beijing 100408, Peoples R China;
5.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China;
6.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China;
7.Chinese Acad Sci, Res Ctr UAV Applicat & Regulat, Beijing 100101, Peoples R China;
推荐引用方式
GB/T 7714		 Dou, Mingyu,Qiu, Shi,Hu, Ming,et al. MCAMamba: Multilevel Cross-Modal Attention-Guided State-Space Model for Multisource Remote Sensing Image Classification[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:4707819.
APA Dou, Mingyu.,Qiu, Shi.,Hu, Ming.,Qiao, Xiaozhen.,Ye, Huping.,...&Sun, Zhe.(2025).MCAMamba: Multilevel Cross-Modal Attention-Guided State-Space Model for Multisource Remote Sensing Image Classification.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,4707819.
MLA Dou, Mingyu,et al."MCAMamba: Multilevel Cross-Modal Attention-Guided State-Space Model for Multisource Remote Sensing Image Classification".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):4707819.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。