Hyperspectral Image Classification Based on Global Spectral Projection and Space Aggregation

Deep learning (DL) based methods, such as the representative vision transformer (ViT) and convolutional neural network (CNN) structures, can characterize spatial-spectral features of hyperspectral images (HSIs) well and achieve outstanding classification performance. Nevertheless, when land cover is complex, the intraclass spectral consistency may be weak and difficult to express effectively in the original data space, leading to potential bias regarding the validity of spatial-spectral information utilization. We propose a new method GSPFormer that first constructs a global spectral projection space (GSPS) to generate land cover more robust representations and enhance the spectral consistency in local neighborhoods. After that, a space aggregation idea is introduced to obtain the central pixel's more abundant spectral feature expression for better classification by fusing all spectral features in the local neighborhood. Extensive experiments are conducted on various HSI datasets for evaluating the classification performance of GSPFormer and other state-of-the-art networks. Comparison results indicate the superiority of the proposed method not only in classification accuracy but also in the number of parameters and convergence. The code of GSPFormer will be found at https://github.com/Preston-Dong/ GSPFormer.