Hyperspectral Image Classification Based on Normalized Grouping Fused Comprehensive Relative Position Transformer Network

In hyperspectral image (HSI) classification, Transformer and CNN are widely used because they complement each other in extracting features. Nevertheless, existing Transformer-based methods still struggle to capture fine-grained local spatial details and positional relationships. Meanwhile, CNN-based attention mechanisms typically process all spectral bands simultaneously to obtain global features, often overlooking locally salient information. To address these challenges, we propose an innovative normalized grouping fused comprehensive relative position transformer network (NG-CRPTN). Specifically, NG-CRPTN comprises two core modules: the comprehensive relative position module (CRPM) and the normalized mutual information band division (NMIBD). The former employs tokens of different dimensions as its foundation, modeling local-to-global spatial structures and relative positional relationships through the local independent relative position transformer (LIRPT) and global independent relative position transformer (GIRPT), while incorporating a local complementary enhancement fusion module (LCEFM) to deeply integrate high and low-frequency information from spatial features across different dimensions. The latter achieves adaptive band grouping of HSI spectral bands to better focus on locally salient features in the spectral dimension. Extensive experiments conducted on four HSI datasets demonstrate that the proposed NG-CRPTN achieves superior classification accuracy with relatively few training samples compared to existing state-of-the-art methods.