Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples

TL;DR

This paper explores using generative adversarial networks to synthesize realistic hyperspectral data, addressing data scarcity and improving classifier training through effective data augmentation.

Contribution

It demonstrates that GANs can generate physically plausible hyperspectral spectra and serve as a valuable data augmentation tool for deep learning models.

Findings

GANs produce genuine-looking hyperspectral spectra

Synthetic data improves classifier performance

Approach validated on multiple public datasets

Abstract

This work addresses the scarcity of annotated hyperspectral data required to train deep neural networks. Especially, we investigate generative adversarial networks and their application to the synthesis of consistent labeled spectra. By training such networks on public datasets, we show that these models are not only able to capture the underlying distribution, but also to generate genuine-looking and physically plausible spectra. Moreover, we experimentally validate that the synthetic samples can be used as an effective data augmentation strategy. We validate our approach on several public hyper-spectral datasets using a variety of deep classifiers.