Self-Supervised Feature Learning Based on Spectral Masking for Hyperspectral Image Classification
文献类型:期刊论文
作者 | Liu, Weiwei4; Liu, Kai3; Sun, Weiwei4; Yang, Gang4; Ren, Kai2; Meng, Xiangchao2; Peng, Jiangtao1 |
刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING |
出版日期 | 2023 |
卷号 | 61页码:15 |
ISSN号 | 0196-2892 |
关键词 | Hyperspectral image (HSI) classification self-supervised feature learning spectral masking |
DOI | 10.1109/TGRS.2023.3310489 |
通讯作者 | Sun, Weiwei(sunweiwei@nbu.edu.cn) |
英文摘要 | Deep learning has emerged as a powerful method for hyperspectral image (HSI) classification. However, a significant prerequisite for HSI classification using deep learning is enough labeled samples, which is both time-consuming and labor-intensive. Yet, labeled samples are essential for training deep learning models. This article proposes an HSI classification method based on the self-supervised learning of spectral masking (SSLSM). The method mainly includes two steps: self-supervised pretraining and fine-tuning. First, considering the rich spectral information of HSI, we propose masked spectral reconstruction as the pretext task. The unmasked data are input into the encoder and decoder sequentially, which are composed of a multilayer transformer, for feature learning of masked spectral reconstruction. Second, we use reference samples to fine-tune the network, and the encoder and decoder are innovatively cascaded for deep semantic feature extraction, which can further improve the ability of feature extraction in the downstream classification tasks. The experimental results show that, compared with other methods, the SSLSM obtains the highest classification accuracy of 96.52%, 97.03%, and 96.70% on the Indian Pines dataset, Pavia University dataset, and Yancheng Wetlands dataset, respectively. Our method can also be applied to other HSI datasets, and the codes will be available from https://github.com/CIRSM-GRoup/2023-TGRS-SSLSM. |
WOS关键词 | NEURAL-NETWORKS ; REPRESENTATION |
WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
WOS记录号 | WOS:001068941300016 |
资助机构 | National Natural Science Foundation of China ; Zhejiang Provincial Natural Science Foundation of China ; Zhejiang Province Pioneering Soldier and Leading Goose Research and Development Project ; Ningbo Science and Technology Innovation 2025 Major Special Project ; Ningbo Natural Science Foundation ; Public Projects of Ningbo City ; Natural Science Foundation of Hubei Province |
源URL | [http://ir.yic.ac.cn/handle/133337/32848] |
专题 | 中国科学院烟台海岸带研究所 |
通讯作者 | Sun, Weiwei |
作者单位 | 1.Hubei Univ, Fac Math & Stat, Hubei Key Lab Appl Math, Wuhan 430062, Peoples R China 2.Ningbo Univ, Fac Elect Engn & Comp Sci, Ningbo 315211, Peoples R China 3.Chinese Acad Sci, Yantai Inst Coastal Zone Res, Yantai 264003, Peoples R China 4.Ningbo Univ, Dept Geog & Spatial Informat Tech, Ningbo 315211, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Weiwei,Liu, Kai,Sun, Weiwei,et al. Self-Supervised Feature Learning Based on Spectral Masking for Hyperspectral Image Classification[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2023,61:15. |
APA | Liu, Weiwei.,Liu, Kai.,Sun, Weiwei.,Yang, Gang.,Ren, Kai.,...&Peng, Jiangtao.(2023).Self-Supervised Feature Learning Based on Spectral Masking for Hyperspectral Image Classification.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,61,15. |
MLA | Liu, Weiwei,et al."Self-Supervised Feature Learning Based on Spectral Masking for Hyperspectral Image Classification".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 61(2023):15. |
入库方式: OAI收割
来源:烟台海岸带研究所
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。