Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples

Nicolas Audebert 1, 2 Bertrand Le Saux 2 Sébastien Lefèvre 1
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
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.
Liste complète des métadonnées

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01809872
Contributor : Nicolas Audebert <>
Submitted on : Thursday, June 7, 2018 - 11:21:56 AM
Last modification on : Tuesday, March 26, 2019 - 2:12:02 PM
Document(s) archivé(s) le : Saturday, September 8, 2018 - 1:23:04 PM

Files

Template.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01809872, version 1
  • ARXIV : 1806.02583

Citation

Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre. Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples. International Geoscience and Remote Sensing Symposium (IGARSS 2018), Jul 2018, Valencia, Spain. ⟨hal-01809872⟩

Share

Metrics

Record views

452

Files downloads

406