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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
RingMo: A Remote Sensing Foundation Model With Masked Image Modeling

文献类型：期刊论文

作者Sun, Xian2,5,6; Wang, Peijin5,6; Lu, Wanxuan5,6; Zhu, Zicong2,5,6; Lu, Xiaonan2,5,6; He, Qibin2,5,6; Li, Junxi2,5,6; Rong, Xuee2,5,6; Yang, Zhujun2,5,6; Chang, Hao2,5,6
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2023
卷号61页码:22
ISSN号0196-2892
关键词Foundation model masked image modeling (MIM) pretraining remote sensing (RS) self-supervised Vision Transformer (ViT)
DOI10.1109/TGRS.2022.3194732
英文摘要Deep learning approaches have contributed to the rapid development of remote sensing (RS) image interpretation. The most widely used training paradigm is to use ImageNet pretrained models to process RS data for specified tasks. However, there are issues such as domain gap between natural and RS scenes and the poor generalization capacity of RS models. It makes sense to develop a foundation model with general RS feature representation. Since a large amount of unlabeled data is available, the self-supervised method has more development significance than the fully supervised method in RS. However, most of the current self-supervised methods use contrastive learning, whose performance is sensitive to data augmentation, additional information, and selection of positive and negative pairs. In this article, we leverage the benefits of generative self-supervised learning (SSL) for RS images and propose an RS foundation model framework called RingMo, which consists of two parts. First, a large-scale dataset is constructed by collecting two million RS images from satellite and aerial platforms, covering multiple scenes and objects around the world. Second, we propose an RS foundation model training method designed for dense and small objects in complicated RS scenes. We show that the foundation model trained on our dataset with RingMo method achieves state-of-the-art (SOTA) on eight datasets across four downstream tasks, demonstrating the effectiveness of the proposed framework. Through in-depth exploration, we believe it is time for RS researchers to embrace generative SSL and leverage its general representation capabilities to speed up the development of RS applications.
资助项目National Key Research and Development Program of China[2021YFB3900504] ; National Natural Science Foundation of China[61725105] ; National Natural Science Foundation of China[62171436]
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:001021331900001
源URL[http://119.78.100.204/handle/2XEOYT63/21267]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Fu, Kun
作者单位1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100190, Peoples R China
3.Huawei, Ascend Comp Ecosyst Enablement Dept, Hangzhou 310000, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
5.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100190, Peoples R China
6.Chinese Acad Sci, Aerosp Informat Res Inst, Key Lab Network Informat Syst Technol NIST, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Sun, Xian,Wang, Peijin,Lu, Wanxuan,et al. RingMo: A Remote Sensing Foundation Model With Masked Image Modeling[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2023,61:22.
APA Sun, Xian.,Wang, Peijin.,Lu, Wanxuan.,Zhu, Zicong.,Lu, Xiaonan.,...&Fu, Kun.(2023).RingMo: A Remote Sensing Foundation Model With Masked Image Modeling.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,61,22.
MLA Sun, Xian,et al."RingMo: A Remote Sensing Foundation Model With Masked Image Modeling".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 61(2023):22.

入库方式： OAI收割

来源：计算技术研究所

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。