GPF-Net: Graph-Polarized Fusion Network for Hyperspectral Image Classification

Recently, there has been growing interest in hyperspectral images (HSIs) classification tasks, with both graph neural networks (GNN) and convolutional neural networks (CNNs) proving to be effective means of analysis. GNN can better capture the spatial structure of HSIs in large target irregular regions through superpixel segmentation, while CNN can refine classification tasks by processing pixel-level features in small target regular regions. However, neither GNN nor CNN models alone can simultaneously consider superpixel-level and pixel-level features to cover both large and small target regions. To fully utilize the strengths of GNN and CNN, we propose a novel model called the graph-polarized fusion (GPF) network. The GPF consists of two branches: the fused GNN (FGNN) classifier in the GNN branch conducts feature learning on large, irregular target regions using both graph convolutional network (GCN) and graph attention network (GAT) as feature extraction operators. The features are integrated using three aggregators, namely, min, max, and weighted add, followed by updating the nodes through 2-D convolutional layers. The polarized neural network (PNN) classifier of the CNN branch primarily works on small, target regular regions using polarized self-attention (PSA) to conduct high-resolution processing on the two dimensions of space and channel without increasing time loss. In addition, GPF employs residual connections to extract features from long distances and multiangles. It also uses weighted fusion to integrate the superpixel-level and pixel-level features obtained from the two branches. Rigorous experiments on five real datasets demonstrate that GPF can fully mine the latent features of HSIs, achieving competitive results compared with other state-of-the-art methods.