Entropy Based Generative Adversarial Network for PolSAR Image Classification
Authors:
- 6 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 132-136
Abstract
In order to solve the problem that the effect of generator feature learning is not paid enough attention in generative adversarial network(GAN) for Polarimetric synthetic aperture radar(PolSAR) data, a new GAN called Entropy-based Auxiliary Classifier Generative Adversarial Networks (E-ACGAN) was proposed in this paper. The decomposition discrepancy was obtained by calculating the entropy decomposition of the real data and the generated data. Then the decomposition discrepancy is used to measure the similarity between the generated data and the real data. This discrepancy will be introduced into the model as an additional optimization goal of the generator. Therefore, the generator can learn more characteristics of PolSAR data to generate more realistic data. In the step of adversarial learning, the discrimination and classification capabilities of the discriminator are also improved with the generator. The experimental results on the Flevoland2 data set show that the classification accuracy of E-ACGAN is 2.36% higher than that of the original ACGAN and it is also improved to different degrees than other traditional classification methods.Keywords
Funding Information
- Innovation Fund
- Research and Development
This publication has 12 references indexed in Scilit:
- Task-Oriented GAN for PolSAR Image Classification and ClusteringIEEE Transactions on Neural Networks and Learning Systems, 2019
- Generative Adversarial Networks: An OverviewIEEE Signal Processing Magazine, 2018
- Object Recognition in Python and MNIST Dataset Modification and Recognition with Five Machine Learning ClassifiersJournal of Image and Graphics, 2018
- Improving Leaf Classification Rate via Background Removal and ROI ExtractionJournal of Image and Graphics, 2016
- Forcing Scale Invariance in Multipolarization SAR Change DetectionIEEE Transactions on Geoscience and Remote Sensing, 2015
- SAR polarimetric change detection for flooded vegetationInternational Journal of Digital Earth, 2013
- Target Scattering Decomposition in Terms of Roll-Invariant Target ParametersIEEE Transactions on Geoscience and Remote Sensing, 2006
- The potential of multifrequency polarimetric SAR in assessing agricultural and arboreous biomassIEEE Transactions on Geoscience and Remote Sensing, 1997
- Classification of multi-look polarimetric SAR imagery based on complex Wishart distributionInternational Journal of Remote Sensing, 1994
- Dr. J. R. Huynen's main contributions in the development of polarimetric radar techniques and how the 'Radar Targets Phenomenological Concept' becomes a theory1993