Hyperspectral images (HSI) have become popular for analysing remotely sensed images in multiple domain like agriculture, medical. However, existing models struggle with complex relationships and characteristics of spectral-spatial data due to the multi-band nature and data redundancy of hyperspectral data. To address this limitation, we propose a new network called DiffSpectralNet, which combines diffusion and transformer techniques. Our approach involves a two-step process. First, we use an unsupervised learning framework based on the diffusion model to extract both high-level and low-level spectral-spatial features. The diffusion method is capable of extracting diverse and meaningful spectral-spatial features, leading to improvement in HSI classification. Then, we employ a pretrained denoising U-Net to extract intermediate hierarchical features for classification. Finally, we use a supervised transformer-based classifier to perform the HSI classification. Through comprehensive experiments on HSI datasets, we evaluate the classification performance of DiffSpectralNet. The results demonstrate that our framework significantly outperforms existing approaches, achieving state-of-the-art performance.

提出了一种名为DiffSpectralNet的新型网络，通过结合扩散和变换器技术，利用无监督学习和预训练去噪U-Net提取高层和低层光谱空间特征，并使用监督变换器分类器进行高光谱图像分类，实现了超越现有方法的创新，达到了最先进的性能。

DiffSpectralNet：揭示扩散模型在高光谱图像分类中的潜力