| Summary: | Deep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods have shone brilliantly in HSI classification. However, understanding how to better exploit spectral and spatial information regarding HSI is still an open area of enquiry. In this article, we propose a hybrid convolution and hybrid resolution network with double attention for HSI classification. First, densely connected 3D convolutional layers are employed to extract preliminary spatial–spectral features. Second, these coarse features are fed to the hybrid resolution module, which mines the features at multiple scales to obtain high-level semantic information and low-level local information. Finally, we introduce a novel attention mechanism for further feature adjustment and refinement. Extensive experiments are conducted to evaluate our model in a holistic manner. Compared to several popular methods, our approach yields promising results for four datasets.
|
|---|