Abstract
Most traditional hyperspectral image (HSI) classification methods relied on hand-crafted or shallow-based descriptors, which limits their applicability and performance. Recently, deep learning has gradually become the mainstream method of HSI classification, because it can automatically extract deep abstract features for classification. However, it remains a challenge to learn more meaningful features for HSI classification from a small training sample set. In this paper, a 3D cascaded spectral–spatial element attention network (3D-CSSEAN) is proposed to solve this issue. The 3D-CSSEAN integrates the spectral–spatial feature extraction and attention area extraction for HSI classification. Two element attention modules in the 3D-CSSEAN enable the deep network to focus on primary spectral features and meaningful spatial features. All attention modules are implemented though several simple activation operations and elementwise multiplication operations. In this way, the training parameters of the network are not added too much, which also makes the network structure suitable for small sample learning. The adopted module cascading pattern not only reduces the computational burden in the deep network but can also be easily operated via plug–expand–play. Experimental results on three public data sets show that the proposed 3D-CSSEAN achieved comparable performance with the state-of-the-art methods.
Highlights
With the development of remote sensing technology, hyperspectral images (HSIs) have been of wide concern and gradually applied in many fields [1,2]
In the past ten years, many works were based on spectral–spatial feature learning for HSI classification [5,6]
3a,4.a In spectral weight vector of the HSI is obtained by global operation of spatial dimenSectionspectral
Summary
With the development of remote sensing technology, hyperspectral images (HSIs) have been of wide concern and gradually applied in many fields [1,2]. In [28], a cascaded dual-scale crossover network (CDSCN) was proposed for HSI classification, which can obtain the parts of interest in the images through the multiplication of dual branch features. These methods use different ways to obtain attention features, thereby improving the classification performance. This method is different from the attention method mentioned above. The proposed described in features, First, a cascade element attention network3D-CSSEAN is proposed model to extract meaningful ods for HSI classification are discussed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have