Generative Adversarial Minority Oversampling for Spectral–Spatial Hyperspectral Image Classification
- 4 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60, 1-15
- https://doi.org/10.1109/tgrs.2021.3052048
Abstract
Recently, convolutional neural networks (CNNs) have exhibited commendable performance for hyperspectral image (HSI) classification. Generally, an important number of samples are needed for each class to properly train CNNs. However, existing HSI data sets suffer from a significant class imbalance problem, where many classes do not have enough samples to characterize the spectral information. The performance of existing CNN models is biased toward the majority classes, which possess more samples for the training. This article addresses this issue of imbalanced data in HSI classification. In particular, a new 3D-HyperGAMO model is proposed, which uses generative adversarial minority oversampling. The proposed 3D-HyperGAMO automatically generates more samples for minority classes at training time, using the existing samples of that class. The samples are generated in the form of a 3-D hyperspectral patch. A different classifier from the generator and the discriminator is used in the 3D-HyperGAMO model, which is trained using both original and generated samples to determine the classes of newly generated samples to which they actually belong. The generated data are combined classwise with the original training data set to learn the network parameters of the class. Finally, the trained 3-D classifier network validates the performance of the model using the test set. Four benchmark HSI data sets, namely, Indian Pines (IP), Kennedy Space Center (KSC), University of Pavia (UP), and Botswana (BW), have been considered in our experiments. The proposed model shows outstanding data generation ability during the training, which significantly improves the classification performance over the considered data sets. The source code is available publicly at https://github.com/mhaut/3D-HyperGAMO .Keywords
Funding Information
- Junta de Extremadura
This publication has 73 references indexed in Scilit:
- To Combat Multi-Class Imbalanced Problems by Means of Over-Sampling TechniquesIEEE Transactions on Knowledge and Data Engineering, 2015
- Deep learningNature, 2015
- Classification of imbalanced data sets using Multi Objective Genetic ProgrammingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Deep Convolutional Neural Networks for Hyperspectral Image ClassificationJournal of Sensors, 2015
- Imbalanced Hyperspectral Image Classification Based on Maximum MarginIEEE Geoscience and Remote Sensing Letters, 2014
- Multiple Feature Learning for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2014
- On the Properties of Neural Machine Translation: Encoder–Decoder ApproachesPublished by Association for Computational Linguistics (ACL) ,2014
- EUSBoost: Enhancing ensembles for highly imbalanced data-sets by evolutionary undersamplingPattern Recognition, 2013
- SMOTE-RSB *: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theoryKnowledge and Information Systems, 2011
- A Randomized Algorithm for Principal Component AnalysisSIAM Journal on Matrix Analysis and Applications, 2010