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

Learning to Propagate Labels on Graphs: An Iterative Multitask Regression Framework for Semi-supervised Hyperspectral Dimensionality Reduction

Hong, Danfeng and Yokoya, Naoto and Chanussot, Jocelyn and Xu, Jian and Zhu, Xiao Xiang (2019) Learning to Propagate Labels on Graphs: An Iterative Multitask Regression Framework for Semi-supervised Hyperspectral Dimensionality Reduction. ISPRS Journal of Photogrammetry and Remote Sensing, 158, pp. 35-49. Elsevier. DOI: 10.1016/j.isprsjprs.2019.09.008 ISSN 0924-2716

[img] PDF - Postprint version (accepted manuscript)
4MB

Official URL: https://www.sciencedirect.com/science/article/pii/S0924271619302199?via%3Dihub

Abstract

Hyperspectral dimensionality reduction (HDR), an important preprocessing step prior to high-level data analysis, has been garnering growing attention in the remote sensing community. Although a variety of methods, both unsupervised and supervised models, have been proposed for this task, yet the discriminative ability in feature representation still remains limited due to the lack of a powerful tool that effectively exploits the labeled and unlabeled data in the HDR process. A semi-supervised HDR approach, called iterative multitask regression (IMR), is proposed in this paper to address this need. IMR aims at learning a low-dimensional subspace by jointly considering the labeled and unlabeled data, and also bridging the learned subspace with two regression tasks: labels and pseudo-labels initialized by a given classifier. More significantly, IMR dynamically propagates the labels on a learnable graph and progressively refines pseudo-labels, yielding a well-conditioned feedback system. Experiments conducted on three widely-used hyperspectral image datasets demonstrate that the dimension-reduced features learned by the proposed IMR framework with respect to classification or recognition accuracy are superior to those of related state-of-the-art HDR approaches.

Item URL in elib:https://elib.dlr.de/129267/
Document Type:Article
Title:Learning to Propagate Labels on Graphs: An Iterative Multitask Regression Framework for Semi-supervised Hyperspectral Dimensionality Reduction
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Hong, Danfengdanfeng.hong (at) dlr.deUNSPECIFIED
Yokoya, NaotoRIKENUNSPECIFIED
Chanussot, Jocelynjocelyn (at) hi.isUNSPECIFIED
Xu, JianDLR-IMF-ATPUNSPECIFIED
Zhu, Xiao Xiangxiao.zhu (at) dlr.deUNSPECIFIED
Date:December 2019
Journal or Publication Title:ISPRS Journal of Photogrammetry and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:158
DOI :10.1016/j.isprsjprs.2019.09.008
Page Range:pp. 35-49
Publisher:Elsevier
ISSN:0924-2716
Status:Published
Keywords:Dimensionality reduction, graph learning, hyperspectral image, iterative, label propagation, multitask regression, remote sensing, semi-supervised.
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
Remote Sensing Technology Institute > Atmospheric Processors
Deposited By: Hong, Danfeng
Deposited On:27 Sep 2019 11:34
Last Modified:04 Dec 2019 17:07

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.