Sample Generation with Self-Attention Generative Adversarial Adaptation Network (SaGAAN) for Hyperspectral Image Classification
Open Access
- 5 March 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (5) , 843
Abstract
Hyperspectral image analysis plays an important role in agriculture, mineral industry, and for military purposes. However, it is quite challenging when classifying high-dimensional hyperspectral data with few labeled samples. Currently, generative adversarial networks (GANs) have been widely used for sample generation, but it is difficult to acquire high-quality samples with unwanted noises and uncontrolled divergences. To generate high-quality hyperspectral samples, a self-attention generative adversarial adaptation network (SaGAAN) is proposed in this work. It aims to increase the number and quality of training samples to avoid the impact of over-fitting. Compared to the traditional GANs, the proposed method has two contributions: (1) it includes a domain adaptation term to constrain generated samples to be more realistic to the original ones; and (2) it uses the self-attention mechanism to capture the long-range dependencies across the spectral bands and further improve the quality of generated samples. To demonstrate the effectiveness of the proposed SaGAAN, we tested it on two well-known hyperspectral datasets: Pavia University and Indian Pines. The experiment results illustrate that the proposed method can greatly improve the classification accuracy, even with a small number of initial labeled samples.Keywords
This publication has 22 references indexed in Scilit:
- Semisupervised Hyperspectral Image Classification With Cluster-Based Conditional Generative Adversarial NetIEEE Geoscience and Remote Sensing Letters, 2019
- Classification of Hyperspectral Images Based on Multiclass Spatial–Spectral Generative Adversarial NetworksIEEE Transactions on Geoscience and Remote Sensing, 2019
- Dimensionality Reduction of Hyperspectral Image Using Spatial Regularized Local Graph Discriminant EmbeddingIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018
- Generative Adversarial Networks for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2018
- An optimization approach to estimate and calibrate column water vapour for hyperspectral airborne dataInternational Journal of Remote Sensing, 2018
- Modified Tensor Locality Preserving Projection for Dimensionality Reduction of Hyperspectral ImagesIEEE Geoscience and Remote Sensing Letters, 2018
- Semisupervised Hyperspectral Image Classification Based on Generative Adversarial NetworksIEEE Geoscience and Remote Sensing Letters, 2017
- Generative Adversarial Networks-Based Semi-Supervised Learning for Hyperspectral Image ClassificationRemote Sensing, 2017
- Generating labeled samples for hyperspectral image classification using correlation of spectral bandsFrontiers of Computer Science, 2015
- Solar Profiles and Spectral Modeling for CPV SimulationsIEEE Journal of Photovoltaics, 2012