Multi-Fake Evolutionary Generative Adversarial Networks for Imbalance Hyperspectral Image Classification

TL;DR

This paper introduces MFEGAN, a novel multi-fake evolutionary GAN framework designed to improve hyperspectral image classification in imbalanced datasets by integrating generative objectives with a discriminator-based classifier.

Contribution

The paper proposes a new multi-fake evolutionary GAN architecture that enhances classification performance for imbalanced hyperspectral data, using a unified discriminator and generator with multiple objectives.

Findings

Outperforms state-of-the-art methods in hyperspectral classification

Effective handling of imbalanced datasets

Validated on two spatial-spectral datasets

Abstract

This paper presents a novel multi-fake evolutionary generative adversarial network(MFEGAN) for handling imbalance hyperspectral image classification. It is an end-to-end approach in which different generative objective losses are considered in the generator network to improve the classification performance of the discriminator network. Thus, the same discriminator network has been used as a standard classifier by embedding the classifier network on top of the discriminating function. The effectiveness of the proposed method has been validated through two hyperspectral spatial-spectral data sets. The same generative and discriminator architectures have been utilized with two different GAN objectives for a fair performance comparison with the proposed method. It is observed from the experimental validations that the proposed method outperforms the state-of-the-art methods with better classification performance.