Hyperspectral imaging provides a useful tool for extracting complex information when visual spectral bands are not enough to solve certain tasks. However, processing hyperspectral images (HSIs) is usually computationally expensive due to the great amount of both spatial and spectral data they incorporate. We present a low-cost convolutional neural network designed for HSI classification. Its architecture consists of two parts: a series of densely connected three-dimensional (3-D) convolutions used as a feature extractor, and a series of two-dimensional (2-D) separable convolutions used as a spatial encoder. We show that this design involves fewer trainable parameters compared to other approaches, yet without detriment to its performance. What is more, we achieve comparable state-of-the-art results testing our architecture on four public remote sensing datasets: Indian Pines, Pavia University, Salinas, and EuroSAT; and a dataset of Kochia leaves [Bassia scoparia] with three different levels of herbicide resistance. The source code and datasets are available online. (Hyper3DNet codebase: https://github.com/GiorgioMorales/hyper3dnet.)

中文翻译：

---

降低成本的高光谱卷积神经网络

当视觉光谱带不足以解决某些任务时，高光谱成像提供了一种提取复杂信息的有用工具。但是，由于高光谱图像（HSI）合并了大量的空间和光谱数据，因此通常在计算上昂贵。我们提出了一种用于HSI分类的低成本卷积神经网络。它的体系结构由两部分组成：用作特征提取器的一系列紧密连接的三维（3-D）卷积，以及用作空间编码器的一系列二维（2-D）可分离卷积。我们表明，与其他方法相比，该设计涉及的可训练参数更少，但又不损害其性能。更，我们在四个公共遥感数据集上测试了我们的体系结构，从而获得了可比的最新结果：印度松树，帕维亚大学，萨利纳斯大学和EuroSAT；以及具有三种不同水平的除草剂抗性的地肤叶[Bassia scoparia]数据集。源代码和数据集可在线获得。（Hyper3DNet代码库：https://github.com/GiorgioMorales/hyper3dnet。）