Hyperspectral image (HSI) data contain rich spectral–spatial information, which can be useful for various applications. Many methods have been proposed to classify the HSIs. Nonetheless, the availability of limited training samples in traditional models frequently weakens their ability to handle the inherent complexity of the task. Deep learning models have been successfully applied in the field of remote sensing. In this letter, we propose a vision transformer (ViT)-based network called hierarchical attention transformer that combines the properties of local representation learning in 3-D and 2-D convolutional neural networks (CNNs) and potent global modeling capabilities in ViT. We leverage the efficiency of window-based self-attention. Within each window, there are dedicated tokens that contribute to both local and global representation learning. The overall accuracy (OA) of the proposed model achieved 99.70%, 99.89%, 99.56%, 81.75%, and 99.59% on five datasets.

中文翻译：

---

用于高光谱图像分类的分层注意力变换器

高光谱图像（HSI）数据包含丰富的光谱空间信息，可用于各种应用。已经提出了许多方法来对 HSI 进行分类。尽管如此，传统模型中有限的训练样本经常削弱它们处理任务固有复杂性的能力。深度学习模型已成功应用于遥感领域。在这封信中，我们提出了一种基于视觉变换器 (ViT) 的网络，称为分层注意力变换器，它结合了 3D 和 2D 卷积神经网络 (CNN) 中局部表示学习的特性以及 ViT 中强大的全局建模功能。我们利用基于窗口的自注意力的效率。在每个窗口内，都有专用的标记，有助于本地和全局表示学习。该模型的总体准确率（OA）在五个数据集上达到了 99.70%、99.89%、99.56%、81.75% 和 99.59%。