Abstract
This paper proposes a novel architecture, termed multiscale principle of relevant information (MPRI), to learn discriminative spectral-spatial features for hyperspectral image 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 http://bit.ly/MPRI_HSI.
Original language | English |
---|---|
Pages (from-to) | 1227-1252 |
Number of pages | 26 |
Journal | Machine Learning |
Volume | 112 |
Issue number | 4 |
DOIs | |
State | Published - Apr 2023 |
Bibliographical note
Publisher Copyright:© 2021, The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature.
Keywords
- Hyperspectral image classification
- Principle of relevant information
- Spectral-spatial pixel characterization
ASJC Scopus subject areas
- Software
- Artificial Intelligence