Hyperspectral images contain rich spatial and spectral information, which provides a strong basis for distinguishing different land-cover objects. Therefore, hyperspectral image (HSI) classification has been a hot research topic. With the advent of deep learning, convolutional neural networks (CNNs) have become a popular method for hyperspectral image classification. However, convolutional neural network (CNN) has strong local feature extraction ability but cannot deal with long-distance dependence well. Vision Transformer (ViT) is a recent development that can address this limitation, but it is not effective in extracting local features and has low computational efficiency. To overcome these drawbacks, we propose a hybrid classification network that combines the strengths of both CNN and ViT, names Spatial-Spectral Former(SSF). The shallow layer employs 3D convolution to extract local features and reduce data dimensions. The deep layer employs a spectral-spatial transformer module for global feature extraction and information enhancement in spectral and spatial dimensions. Our proposed model achieves promising results on widely used public HSI datasets compared to other deep learning methods, including CNN, ViT, and hybrid models.

中文翻译：

---

用于高光谱图像分类的三重结构变换器

高光谱图像包含丰富的空间和光谱信息，为区分不同的土地覆盖物体提供了强有力的基础。因此，高光谱图像（HSI）分类一直是研究热点。随着深度学习的出现，卷积神经网络（CNN）已成为高光谱图像分类的流行方法。然而，卷积神经网络（CNN）具有很强的局部特征提取能力，但不能很好地处理长距离依赖。 Vision Transformer（ViT）是最近的发展，可以解决这个限制，但它在提取局部特征方面效果不佳，并且计算效率较低。为了克服这些缺点，我们提出了一种结合了 CNN 和 ViT 优点的混合分类网络，称为空间谱形成器（SSF）。浅层采用3D卷积来提取局部特征并降低数据维度。深层采用光谱空间变换器模块进行全局特征提取以及光谱和空间维度的信息增强。与其他深度学习方法（包括 CNN、ViT 和混合模型）相比，我们提出的模型在广泛使用的公共 HSI 数据集上取得了有希望的结果。