KMS Chongqing Institute of Green and Intelligent Technology, CAS
Multi-Structure KELM With Attention Fusion Strategy for Hyperspectral Image Classification | |
Sun, Le1,2; Fang, Yu1; Chen, Yuwen3; Huang, Wei4; Wu, Zebin5; Jeon, Byeungwoo6 | |
2022 | |
摘要 | Hyperspectral image (HSI) classification refers to accurately corresponding each pixel in an HSI to a land-cover label. Recently, the successful application of multiscale and multifeature methods has greatly improved the performance of HSI classification due to their enhanced utilization of the available spectral-spatial information. However, as the number of scales and the number of features increases, it becomes more difficult to achieve an optimal degree of fusion for multiple classifiers [e.g., kernel extreme learning machine (KELM)]. On the other hand, a limited sample size of the HSI may cause overfitting problems, which seriously affects the classification accuracy. Therefore, in this article, a novel multi-structure KELM with attention fusion strategy (MSAF-KELM) is proposed to achieve accurate fusion of multiple classifiers for effective HSI classification with ultrasmall sample rates. First, a multi-structure network is built, which combines multiple scales and multiple features to extract abundant spectral-spatial information. Second, a fast and efficient KELM is employed to enable rapid classification. Finally, a weighted self-attention fusion strategy (WSAFS) is introduced, which combines the output weights of each KELM subbranch and the self-attention mechanism to achieve an efficient fusion result on multi-structure networks. We conducted experiments on four types of HSI datasets with different evaluation methods and compared them with several classical and state-of-the-art methods, which demonstrate the excellent performance of our method on ultrasmall sample rates. The code is available at https://github.com/Fang666666/MSAF-KELM for reproducibility. |
关键词 | Feature extraction Training Deep learning Kernel Hyperspectral imaging Electronic mail Extreme learning machines Attention mechanisms hyperspectral image (HSI) classification kernel extreme learning machine (KELM) multifeature multiscale (MS) |
DOI | 10.1109/TGRS.2022.3208165 |
发表期刊 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING |
ISSN | 0196-2892 |
卷号 | 60页码:17 |
通讯作者 | Huang, Wei(hnhw235@163.com) |
收录类别 | SCI |
WOS记录号 | WOS:000864196200001 |
语种 | 英语 |