Deep learning has achieved promising performance in hyperspectral image (HSI) classification. Training deep models usually requires labeling massive HSIs, which, however, is prohibitively time-consuming and expensive. To fill in the gap, this article proposes a novel meta-learning method for HSI few-shot classification that conducts HSI classification with a few labeled samples. Specifically, we introduce the Earth mover’s distance (EMD) as a metric. The designed EMD metric learning module aims to calculate the similarity of paired embedding features by decomposing embedding features into a set of local representations. The EMD metric aims to find the optimal matching flows between local representations that have the minimum matching cost. Furthermore, we attempt to learn class prototype representation for each hyperspectral class using the EMD metric. The proposed network effectively learns general knowledge from base HSIs and transfers such knowledge to the classification of novel HSIs. We conduct HSI few-shot classification by training on three base HSIs and classification on three novel HSIs. Extensive experimental results on three novel HSI datasets demonstrate that the proposed model outperforms the existing state-of-the-art HSI methods, including two HSI few-shot methods.

中文翻译：

---

基于推土机距离的高光谱图像少样本分类网络


深度学习在高光谱图像（HSI）分类方面取得了令人鼓舞的性能。训练深度模型通常需要标记大量 HSI，然而，这非常耗时且昂贵。为了填补这一空白，本文提出了一种新颖的 HSI 少样本分类元学习方法，该方法用少量标记样本进行 HSI 分类。具体来说，我们引入地球移动器距离（EMD）作为度量。设计的 EMD 度量学习模块旨在通过将嵌入特征分解为一组局部表示来计算成对嵌入特征的相似度。 EMD 度量旨在找到具有最小匹配成本的局部表示之间的最佳匹配流。此外，我们尝试使用 EMD 度量来学习每个高光谱类的类原型表示。所提出的网络有效地从基础 HSI 中学习一般知识，并将这些知识转移到新 HSI 的分类中。我们通过对三个基础 HSI 进行训练并对三个新 HSI 进行分类来进行 HSI 少样本分类。对三个新颖的 HSI 数据集的大量实验结果表明，所提出的模型优于现有最先进的 HSI 方法，包括两种 HSI 少样本方法。