elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Generative Adversarial Networks for Hyperspectral Image Classification

Lin, Zhu and Chen, Yushi and Ghamisi, Pedram and Benediktsson, Jon Atli (2018) Generative Adversarial Networks for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 56 (9), pp. 5046-5063. IEEE - Institute of Electrical and Electronics Engineers. DOI: 10.1109/TGRS.2018.2805286 ISSN 0196-2892

[img] PDF
1MB

Official URL: http://ieeexplore.ieee.org/document/8307247/

Abstract

A generative adversarial network (GAN) usually contains a generative network and a discriminative network in competition with each other. The GAN has shown its capability in a variety of applications. In this paper, the usefulness and effectiveness of GAN for classification of hyperspectral images (HSIs) are explored for the first time. In the proposed GAN, a convolutional neural network (CNN) is designed to discriminate the inputs and another CNN is used to generate so-called fake inputs. The aforementioned CNNs are trained together: the generative CNN tries to generate fake inputs that are as real as possible, and the discriminative CNN tries to classify the real and fake inputs. This kind of adversarial training improves the generalization capability of the discriminative CNN, which is really important when the training samples are limited. Specifically, we propose two schemes: 1) a well-designed 1D-GAN as a spectral classifier and 2) a robust 3D-GAN as a spectral–spatial classifier. Furthermore, the generated adversarial samples are used with real training samples to fine-tune the discriminative CNN, which improves the final classification performance. The proposed classifiers are carried out on three widely used hyperspectral data sets: Salinas, Indiana Pines, and Kennedy Space Center. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods. In addition, the proposed GANs open new opportunities in the remote sensing community for the challenging task of HSI classification and also reveal the huge potential of GAN-based methods for the analysis of such complex and inherently nonlinear data.

Item URL in elib:https://elib.dlr.de/119294/
Document Type:Article
Title:Generative Adversarial Networks for Hyperspectral Image Classification
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Lin, ZhuHarbin Institute of TechnologyUNSPECIFIED
Chen, YushiHarbin Institute of TechnologyUNSPECIFIED
Ghamisi, PedramDLR-IMF/TUM-LMFUNSPECIFIED
Benediktsson, Jon AtliFaculty of Electrical and Computer Engineering, University of Iceland, 107 Reykjavik, IcelandUNSPECIFIED
Date:March 2018
Journal or Publication Title:IEEE Transactions on Geoscience and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:56
DOI :10.1109/TGRS.2018.2805286
Page Range:pp. 5046-5063
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:0196-2892
Status:Published
Keywords:Convolutional neural network (CNN), deep learning, generative adversarial network (GAN), hyperspectral image (HSI) classification
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > SAR Signal Processing
Deposited By: Ghamisi, Pedram
Deposited On:13 Mar 2018 12:16
Last Modified:31 Jul 2019 20:16

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.