Multiscale Principle of Relevant Information for Hyperspectral Image Classification

2019/07/13 by Yantao Wei, Shujian Yu, Wei, Yantao +5
Computer Science · Engineering · Mathematics · #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #eess.IV #electronic engineering #information engineering #stat.ML

paper · pdf · doi:10.48550/arxiv.1907.06022

Mansucript to be published in Machine Learning Journal (Springer). Code available at https://github.com/SJYuCNEL/Principle-of-Relevant-Information-and-HSI-Classification

arxiv created 2021/06/05 · arxiv updated 2021/06/08

Abstract

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 \urlhttp://bit.ly/MPRI_HSI.

Related

• Dimensionality Reduction and Classification Feature Using Mutual Information Applied to Hyperspectral Images: A Wrapper Strategy Algorithm Based on Minimizing the Error Probability Using the Inequality of Fano
• AI-Driven Hyperspectral Image Classification using Low-Rank Representation and Spatial-Spectral Information
• Combining multiscale features for classification of hyperspectral images: a sequence based kernel approach
• Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques
• A 3-stage Spectral-spatial Method for Hyperspectral Image Classification