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

Fully conv-deconv network for unsupervised spectral-spatial feature extraction of hyperspectral imagery via residual learning

Mou, Lichao and Ghamisi, Pedram and Zhu, Xiaoxiang (2017) Fully conv-deconv network for unsupervised spectral-spatial feature extraction of hyperspectral imagery via residual learning. In: Proceedings of IGARSS 2017, pp. 1-4. IEEE Xplore. IGARSS 2017, 23.-28. Juli 2017, Fort Worth, TX, USA.

[img] PDF
1MB

Official URL: http://www.igarss2017.org/

Abstract

Supervised approaches classify input data using a set of representative samples for each class, known as training samples. The collection of such samples are expensive and time-demanding. Hence, unsupervised feature learning, which has a quick access to arbitrary amount of unlabeled data, is conceptually of high interest. In this paper, we propose a novel network architecture, fully Conv-Deconv network with residual learning, for unsupervised spectral-spatial feature learning of hyperspectral images, which is able to be trained in an end-to-end manner. Specifically, our network is based on the so-called encoder-decoder paradigm, i.e., the input 3D hyperspectral patch is first transformed into a typically lower-dimensional space via a convolutional sub-network (encoder), and then expanded to reproduce the initial data by a deconvolutional sub-network (decoder). Experimental results on the Pavia University hyperspectral data set demonstrate competitive performance obtained by the proposed methodology compared to other studied approaches.

Item URL in elib:https://elib.dlr.de/118271/
Document Type:Conference or Workshop Item (Speech)
Title:Fully conv-deconv network for unsupervised spectral-spatial feature extraction of hyperspectral imagery via residual learning
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Mou, Lichaolichao.mou (at) dlr.deUNSPECIFIED
Ghamisi, PedramDLR-IMF/TUM-LMFUNSPECIFIED
Zhu, Xiaoxiangxiao.zhu (at) dlr.deUNSPECIFIED
Date:July 2017
Journal or Publication Title:Proceedings of IGARSS 2017
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 1-4
Publisher:IEEE Xplore
Status:Published
Keywords:Convolutional network, deconvolutional network, hyperspectral image classification, residual learning, unsupervised spectral-spatial feature learning
Event Title:IGARSS 2017
Event Location:Fort Worth, TX, USA
Event Type:international Conference
Event Dates:23.-28. Juli 2017
Organizer:IEEE
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > SAR Signal Processing
Deposited By: Mou, LiChao
Deposited On:18 Jan 2018 13:35
Last Modified:31 Jul 2019 20:15

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.