Graph-Based Semisupervised Learning With Weighted Features for Hyperspectral Remote Sensing Image Classification

Graph neural network has an excellent performance in obtaining the similarity relationship of samples, so it has been widely used in computer vision. But the hyperspectral remote sensing image (HSI) has some problems, such as data redundancy, noise, lack of labeled samples, and insufficient utilization of spatial information. These problems affect the accuracy of HSI classification using graph neural networks. To solve the aforementioned problems, this article proposes graph-based semisupervised learning with weighted features for HSI classification. The method proposed in this article first uses the stacked autoencoder network to extract features, which is used to remove the redundancy of HSI data. Then, the similarity attenuation coefficient is introduced to improve the original feature weighting scheme. In this way, the contribution difference of adjacent pixels to the center pixel is reflected. Finally, to obtain more generalized spectral features, a shallow feature extraction mechanism is added to the stacked autoencoder network. And features that have good generalization can solve the problem of the lack of labeled samples. The experiment on three different types of datasets demonstrates that the proposed method in this article can get better classification performance in the case of the scarcity of labeled samples than other classification methods.