Abstract | ||
---|---|---|
In recent years, convolutional neural networks (CNNs) have been widely used in hyperspectral images (HSIs) classification. However, 2-D CNN, 3-D CNN, and even the newly emerged hybrid CNN (HCNN) all require multiple or deep CNN layers to obtain excellent classification performance, which inevitably results in the high complexity and the need for a large number of training samples. Moreover, as a local operator, convolution is challenging to fully use global information. To solve the above two issues, we design a HCNN based on global reasoning (GloRe-HCNN) for HSI classification. On the one hand, the GloRe-HCNN uses only one layer of 3-D CNN and one layer of 2-D CNN to jointly extract the spatial-spectral features of HSI. On the other hand, we contrive a spatial-spectral global reasoning unit (SS-GloRe-Unit) to take the place of stacked multilayer 3-D CNN for extracting global features fully. We select small training samples in three standard datasets and compare them with state-of-the-art CNN methods. Numerous experiments show that our GloRe-HCNN performs advanced performance. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/LGRS.2022.3199208 | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS |
Keywords | DocType | Volume |
Training, Solid modeling, Geoscience and remote sensing, Feature extraction, Nonhomogeneous media, Cognition, Convolutional neural networks, Hybrid convolutional neural network (HCNN), hyperspectral image (HSI) classification, small training samples, spatial-spectral global reasoning unit (SS-GloRe-Unit) | Journal | 19 |
ISSN | Citations | PageRank |
1545-598X | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wuli Wang | 1 | 0 | 0.68 |
Xiaohu Ma | 2 | 0 | 0.34 |
Linchun Leng | 3 | 0 | 0.34 |
Yanjiang Wang | 4 | 15 | 8.65 |
Bao-Di Liu | 5 | 166 | 27.34 |
Jinfeng Sun | 6 | 0 | 0.34 |