RingMo: A Remote Sensing Foundation Model With Masked Image Modeling
Chinese Academy of Sciences · Aerospace Information Research Institute · +4 more institutions
Abstract
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…
Citation impact
- FWCI
- 28.25
- Percentile
- 100%
- References
- 187
Authors
15- XSXian SunCorresponding
Chinese Academy of Sciences, Aerospace Information Research Institute, University of Chinese Academy of Sciences
- PWPeijin Wang
Chinese Academy of Sciences, Aerospace Information Research Institute
- WLWanxuan Lu
Chinese Academy of Sciences, Aerospace Information Research Institute
- ZZZicong Zhu
Chinese Academy of Sciences, Aerospace Information Research Institute, University of Chinese Academy of Sciences
- XLXiaonan Lü
Chinese Academy of Sciences, Aerospace Information Research Institute, University of Chinese Academy of Sciences
Topics & keywords
- Computer science
- Leverage (statistics)
- Artificial intelligence
- Generalization
- Feature learning
- Deep learning
- Machine learning
- Representation (politics)
- No poverty