dc.contributor |
Háskóli Íslands |
dc.contributor |
University of Iceland |
dc.contributor.author |
Hong, Danfeng |
dc.contributor.author |
Chanussot, Jocelyn |
dc.contributor.author |
Yokoya, Naoto |
dc.contributor.author |
Kang, Jian |
dc.contributor.author |
Zhu, Xiao Xiang |
dc.date.accessioned |
2020-12-07T13:58:46Z |
dc.date.available |
2020-12-07T13:58:46Z |
dc.date.issued |
2020-08 |
dc.identifier.citation |
Hong, D., Chanussot, J., Yokoya, N., Kang, J., Zhu, X.X., 2020. Learning-Shared Cross-Modality Representation Using Multispectral-LiDAR and Hyperspectral Data. IEEE Geoscience and Remote Sensing Letters. doi:10.1109/lgrs.2019.2944599 |
dc.identifier.issn |
1545-598X |
dc.identifier.issn |
1558-0571 (eISSN) |
dc.identifier.uri |
https://hdl.handle.net/20.500.11815/2275 |
dc.description |
Publisher's version (útgefin grein) |
dc.description.abstract |
Due to the ever-growing diversity of the data source, multimodality feature learning has attracted more and more attention. However, most of these methods are designed by jointly learning feature representation from multimodalities that exist in both training and test sets, yet they are less investigated in the absence of certain modality in the test phase. To this end, in this letter, we propose to learn a shared feature space across multimodalities in the training process. By this way, the out-of-sample from any of multimodalities can be directly projected onto the learned space for a more effective cross-modality representation. More significantly, the shared space is regarded as a latent subspace in our proposed method, which connects the original multimodal samples with label information to further improve the feature discrimination. Experiments are conducted on the multispectral-Light Detection and Ranging (LIDAR) and hyperspectral data set provided by the 2018 IEEE GRSS Data Fusion Contest to demonstrate the effectiveness and superiority of the proposed method in comparison with several popular baselines. |
dc.description.sponsorship |
This work was supported in part by the German Research Foundation (DFG) under Grant ZH 498/7-2, in part by the Helmholtz Association under the framework of the Young Investigators Group SiPEO (VH-NG-1018), and in part by the European Research Council (ERC) under the European Unions Horizon 2020 Research and Innovation Program (Grant agreement No. ERC-2016-StG-714087, Acronym: So2Sat). The work of Naoto Yokoya was supported by the Japan Society for the Promotion of Science (KAKENHI) under Grant 18K18067. (Corresponding author: Xiao Xiang Zhu.) Danfeng Hong and Xiao Xiang Zhu are with the Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR), 82234 Wessling, Germany, and also with Signal Processing in Earth Observation (SiPEO), Technical University of Munich (TUM), 80333 Munich, Germany (e-mail: danfeng.hong@dlr.de; xiaoxiang.zhu@dlr.de). |
dc.format.extent |
1470-1474 |
dc.language.iso |
en |
dc.publisher |
Institute of Electrical and Electronics Engineers (IEEE) |
dc.relation |
info:eu-repo/grantAgreement/EC/H2020/714087 |
dc.relation.ispartofseries |
IEEE Geoscience and Remote Sensing Letters;17(8) |
dc.rights |
info:eu-repo/semantics/openAccess |
dc.subject |
Cross-modality |
dc.subject |
Feature learning |
dc.subject |
Hyperspectral |
dc.subject |
Multimodality |
dc.subject |
Multispectral-Light Detection and Ranging |
dc.subject |
Shared subspace learning |
dc.subject |
Fjarkönnun |
dc.title |
Learning-Shared Cross-Modality Representation Using Multispectral-LiDAR and Hyperspectral Data |
dc.type |
info:eu-repo/semantics/article |
dcterms.license |
This work is licensed under a Creative Commons Attribution 4.0 License. Formore information, see https://creativecommons.org/licenses/by/4.0/ |
dc.description.version |
Peer Reviewed |
dc.identifier.journal |
IEEE Geoscience and Remote Sensing Letters |
dc.identifier.doi |
10.1109/LGRS.2019.2944599 |
dc.relation.url |
http://xplorestaging.ieee.org/ielx7/8859/9145892/08976086.pdf?arnumber=8976086 |
dc.contributor.department |
Rafmagns- og tölvuverkfræðideild (HÍ) |
dc.contributor.department |
Faculty of Electrical and Computer Engineering (UI) |
dc.contributor.school |
Verkfræði- og náttúruvísindasvið (HÍ) |
dc.contributor.school |
School of Engineering and Natural Sciences (UI) |