This paper proposes a novel architecture, termed multiscale principle of relevant information (MPRI), to learn discriminative spectral-spatial features for hyperspectral image (HSI) classification. MPRI inherits the merits of the principle of relevant information (PRI) to effectively extract multiscale information embedded in the given data, and also takes advantage of the multilayer structure to learn representations in a coarse-to-fine manner. Specifically, MPRI performs spectral-spatial pixel characterization (using PRI) and feature dimensionality reduction (using regularized linear discriminant analysis) iteratively and successively. Extensive experiments on three benchmark data sets demonstrate that MPRI outperforms existing state-of-the-art methods (including deep learning based ones) qualitatively and quantitatively, especially in the scenario of limited training samples. Code of MPRI is available at \url{http://bit.ly/MPRI_HSI}.
翻译:本文提出一个新的结构,称为相关信息的多尺度原则(MPRI),以学习用于超光谱图像分类的歧视性光谱空间特征(HSI),MPRI继承了相关信息原则(PRI)的优点,以有效提取特定数据所含的多尺度信息,并利用多层次结构以粗略到松绑的方式学习表达方式。具体地说,MPRI以迭接和连续的方式(使用PRI)进行光谱-空间像素定性(使用PRI)和特征维度降低(使用常规线性线性分析)。关于三个基准数据集的广泛实验表明,MPRI在质量和数量上超过了现有最先进的方法(包括基于深度学习的方法),特别是在有限的培训样本的情况下。