HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model
Wuhan University · State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing · +3 more institutions
Abstract
Accurate hyperspectral image (HSI) interpretation is critical for providing valuable insights into various earth observation-related applications such as urban planning, precision agriculture, and environmental monitoring. However, existing HSI processing methods are predominantly task-specific and scene-dependent, which severely limits their ability to transfer knowledge across tasks and scenes, thereby reducing the practicality in real-world applications. To address these challenges, we present HyperSIGMA, a vision transformer-based foundation model that unifies HSI interpretation across tasks and scenes, scalable to over one billion parameters. To overcome the spectral and spatial redundancy inherent in…
Citation impact
- FWCI
- 99.60
- Percentile
- 100%
- References
- 156
Authors
22- DWDi WangCorresponding
Wuhan University
- MHMeiqi Hu
Wuhan University, State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
- YJYao Jin
Wuhan University, State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
- YMYuchun Miao
Wuhan University
- JYJiaqi Yang
Wuhan University, State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing
Topics & keywords
- Hyperspectral imaging
- Artificial intelligence
- Computer science
- Foundation (evidence)
- Comprehension
- Machine learning
- Geography