Abstract | ||
---|---|---|
This study presents a spectral-spatial self-attention network (SSSAN) for classification of hyperspectral images (HSIs), which can adaptively integrate local features with long-range dependencies related to the pixel to be classified. Specifically, it has two subnetworks. The spatial subnetwork introduces the proposed spatial self-attention module to exploit rich patch-based contextual information related to the center pixel. The spectral subnetwork introduces the proposed spectral self-attention module to exploit the long-range spectral correlation over local spectral features. The extracted spectral and spatial features are then adaptively fused for HSI classification. Experiments conducted on four HSI datasets demonstrate that the proposed network outperforms several state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TGRS.2021.3102143 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING |
Keywords | DocType | Volume |
Feature extraction, Correlation, Convolutional neural networks, Image segmentation, Convolution, Hyperspectral imaging, Adaptation models, Convolutional neural network (CNN), deep learning, hyperspectral image (HSI) classification, spatial self-attention module, spectral self-attention module | Journal | 60 |
ISSN | Citations | PageRank |
0196-2892 | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xuming Zhang | 1 | 0 | 0.34 |
Genyun Sun | 2 | 149 | 17.27 |
Xiuping Jia | 3 | 1424 | 126.54 |
Lixin Wu | 4 | 94 | 35.60 |
Aizhu Zhang | 5 | 0 | 1.01 |
Jinchang Ren | 6 | 1144 | 88.54 |
Hang Fu | 7 | 0 | 1.01 |
Yanjuan Yao | 8 | 0 | 0.34 |