Hyperspectral Image Classification Based on Multiscale Feature Search Graph Convolutional Network With Meta Pseudolabels

In recent years, graph convolutional networks (GCNs) have been introduced for hyperspectral image (HSI) classification due to their ability to effectively process the inherent graph structure of HSI data. However, existing GCN-based methods heavily rely on manually selecting superpixel segmentation scales, which limits their ability to capture multiscale contextual relationships adaptively. Moreover, the scarcity of labeled samples in HSI data further degrades the model’s robustness. To address these challenges, we propose a novel semisupervised framework—multiscale feature search GCN with meta pseudolabels (MFSGCN-MPL). First, the HSIs are segmented into superpixels of different scales, transforming them into a graph structure. After that, a neural network search algorithm is used to optimize the combination of superpixel feature weights, improving the discriminability of feature expression. Finally, meta pseudolabels are generated based on a semisupervised teacher–student model that shares the same GCN, and the student network is fine-tuned to enhance its robustness. The proposed MFSGCN-MPL model is implemented on three commonly used HSI datasets and compared with some semisupervised and supervised classification methods. The results confirmed that the proposed model automatically captured features and achieved higher classification accuracies under small sample conditions.