论文标题
Litedensenet：用于高光谱图像分类的轻量级网络
LiteDenseNet: A Lightweight Network for Hyperspectral Image Classification
论文作者
论文摘要
近年来，基于深度学习的高光谱图像（HSI）分类一直是一个有吸引力的领域。但是，作为一种数据驱动的算法，深度学习方法通常需要大量的计算资源和高质量的标签数据集，而高性能计算和数据注释的成本却很昂贵。在本文中，为了减少对大量计算和标记样品的依赖，我们提出了基于densenet的轻质网络结构（Litedensenet），以进行高光谱图像分类。受Googlenet和Peleenet的启发，我们设计了一个3D双向密集层，以捕获输入的本地和全局特征。由于卷积是计算密集型操作，因此我们引入了群卷，以进一步降低计算成本和参数大小。因此，观察到的参数数量和计算的消耗远小于对互动深度学习方法，这意味着Litedensenet拥有更简单的体系结构和更高的效率。在6种广泛使用的高光谱数据集中进行的一系列定量体验表明，即使缺少标记的样品很严重，提出的Litedenset也获得了最先进的性能。
Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, deep learning method usually requires numerous computational resources and high-quality labelled dataset, while the cost of high-performance computing and data annotation is expensive. In this paper, to reduce dependence on massive calculation and labelled samples, we propose a lightweight network architecture (LiteDenseNet) based on DenseNet for Hyperspectral Image Classification. Inspired by GoogLeNet and PeleeNet, we design a 3D two-way dense layer to capture the local and global features of the input. As convolution is a computationally intensive operation, we introduce group convolution to decrease calculation cost and parameter size further. Thus, the number of parameters and the consumptions of calculation are observably less than contrapositive deep learning methods, which means LiteDenseNet owns simpler architecture and higher efficiency. A series of quantitative experiences on 6 widely used hyperspectral datasets show that the proposed LiteDenseNet obtains the state-of-the-art performance, even though when the absence of labelled samples is severe.
