Multiscale Principle of Relevant Information for Hyperspectral Image Classification
This work addresses hyperspectral image classification, a domain-specific problem, with an incremental improvement over existing methods.
The paper tackles hyperspectral image classification by proposing the multiscale principle of relevant information (MPRI) architecture, which learns discriminative spectral-spatial features and outperforms state-of-the-art methods, especially with limited training samples, as shown in experiments on three benchmark datasets.
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}.