metadata
license: apache-2.0
pipeline_tag: image-feature-extraction
library_name: transformers
HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model
HyperSIGMA is the first billion-level foundation model specifically designed for hyperspectral image (HSI) interpretation. It introduces a novel sparse sampling attention (SSA) mechanism to address spectral and spatial redundancy in HSIs, effectively promoting the learning of diverse contextual features. HyperSIGMA integrates spatial and spectral features using a specially designed spectral enhancement module. It was trained on the large-scale HyperGlobal-450K dataset, which contains over 20 million three-band images.
- Paper: HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model
- Code: https://github.com/WHU-Sigma/HyperSIGMA
- Dataset: https://huggingface.co/datasets/WHU-Sigma/HyperGlobal-450K
Citation
@article{hypersigma,
title={HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model},
author={Wang, Di and Hu, Meiqi and Jin, Yao and Miao, Yuchun and Yang, Jiaqi and Xu, Yichu and Qin, Xiaolei and Ma, Jiaqi and Sun, Lingyu and Li, Chenxing and Fu, Chuan and Chen, Hongruixuan and Han, Chengxi and Yokoya, Naoto and Zhang, Jing and Xu, Minqiang and Liu, Lin and Zhang, Lefei and Wu, Chen and Du, Bo and Tao, Dacheng and Zhang, Liangpei},
journal={arXiv preprint arXiv:2406.11519},
year={2024}
}