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

WU-Net: A Weakly-supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery

Hong, Danfeng and Chanussot, Jocelyn and Yokoya, Naoto and Heiden, Uta and Heldens, Wieke and Zhu, Xiao Xiang (2019) WU-Net: A Weakly-supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery. In: 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1-4. IGARSS2019, 28. Juli - 2. Áug. 2019, Yokohama, Japan.

[img] PDF


Recently, enormous efforts have been made to improve the performance of the linear or nonlinear mixing model for hyperspectral unmixing, yet their ability to handle spectral variability and extract physically meaningful endmembers remains limited. Based on the powerful learning ability of deep learning, we propose a weakly-supervised unmixing network, called WU-Net, to break the bottleneck. Beyond the autoencoder-like architecture, WU-Net learns an additional network from the pure or nearly-pure endmembers to correct the weights of another unmixing network towards a more accurate and interpretable unmixing solution, thus yielding a two-stream deep network. Experimental results conducted on two different datasets, one fully artificial simulation dataset and one simulated EnMap dataset generated from a real HyMap dataset, demonstrate the effectiveness and superiority of WU-Net over several state-of-the-art algorithms

Item URL in elib:https://elib.dlr.de/128489/
Document Type:Conference or Workshop Item (Speech)
Title:WU-Net: A Weakly-supervised Unmixing Network for Remotely Sensed Hyperspectral Imagery
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Hong, Danfengdanfeng.hong (at) dlr.deUNSPECIFIED
Chanussot, Jocelynjocelyn (at) hi.isUNSPECIFIED
Yokoya, Naotonaoto.yokoya (at) riken.jpUNSPECIFIED
Heiden, Utauta.heiden (at) dlr.deUNSPECIFIED
Heldens, WiekeWieke.Heldens (at) dlr.dehttps://orcid.org/0000-0001-6209-5664
Zhu, Xiao Xiangxiao.zhu (at) dlr.deUNSPECIFIED
Journal or Publication Title:2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 1-4
Keywords:Deep learning, hyperspectral imagery,remote sensing, spectral unmixing, two-stream network,weakly-supervised, HyMap, EnMAP
Event Title:IGARSS2019
Event Location:Yokohama, Japan
Event Type:international Conference
Event Dates:28. Juli - 2. Áug. 2019
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 > EO Data Science
German Remote Sensing Data Center > Land Surface Dynamics
Deposited By: Hong, Danfeng
Deposited On:22 Jul 2019 13:23
Last Modified:01 Oct 2019 03:00

Repository Staff Only: item control page

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