Generative Adversarial Networks and Probabilistic Graph Models for Hyperspectral Image Classification

TL;DR

This paper introduces a novel framework combining GANs and probabilistic graphical models to improve hyperspectral image classification, effectively utilizing unlabeled data and capturing spectral-spatial features.

Contribution

It proposes an integrated spectral-spatial GAN and conditional random field approach for hyperspectral classification, addressing spectral-spatial characteristics and unlabeled data utilization.

Findings

Achieved high classification accuracy with limited training data.

Effectively leveraged unlabeled data for improved performance.

Demonstrated robustness on standard hyperspectral datasets.

Abstract

High spectral dimensionality and the shortage of annotations make hyperspectral image (HSI) classification a challenging problem. Recent studies suggest that convolutional neural networks can learn discriminative spatial features, which play a paramount role in HSI interpretation. However, most of these methods ignore the distinctive spectral-spatial characteristic of hyperspectral data. In addition, a large amount of unlabeled data remains an unexploited gold mine for efficient data use. Therefore, we proposed an integration of generative adversarial networks (GANs) and probabilistic graphical models for HSI classification. Specifically, we used a spectral-spatial generator and a discriminator to identify land cover categories of hyperspectral cubes. Moreover, to take advantage of a large amount of unlabeled data, we adopted a conditional random field to refine the preliminary classification results generated by GANs. Experimental results obtained using two commonly studied datasets demonstrate that the proposed framework achieved encouraging classification accuracy using a small number of data for training.