elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Unsupervised Spectral-Spatial Feature Learning via Deep Residual Conv-Deconv Network for Hyperspectral Image Classification

Mou, Lichao und Ghamisi, Pedram und Zhu, Xiao Xiang (2018) Unsupervised Spectral-Spatial Feature Learning via Deep Residual Conv-Deconv Network for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 56 (1), Seiten 391-406. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/TGRS.2017.2748160. ISSN 0196-2892.

[img] PDF
7MB

Offizielle URL: http://ieeexplore.ieee.org/document/8082108/

Kurzfassung

Supervised approaches classify input data using a set of representative samples for each class, known as Training samples. The collection of such samples is expensive and time demanding. Hence, unsupervised feature learning, which has a quick access to arbitrary amounts of unlabeled data, is conceptually of high interest. In this paper, we propose a novel network architecture, fully Conv–Deconv network, 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 3-D hyperspectral patch is first transformed into a typically lower dimensional space via a convolutional subnetwork (encoder), and then expanded to reproduce the initial data by a deconvolutional subnetwork (decoder). However, during the experiment, we found that such a network is not easy to be optimized. To address this problem, we refine the proposed network architecture by incorporating: 1) residual learning and 2) a new unpooling operation that can use memorized max-pooling indexes. Moreover, to understand the “black box,” we make an in-depth study of the learned Feature maps in the experimental analysis. A very interesting discovery is that some specific “neurons” in the first residual block of the proposed network own good description power for semantic visual patterns in the object level, which provide an opportunity to achieve “free” object detection. This paper, for the first time in the remote sensing community, proposes an end-to-end fully Conv–Deconv network for unsupervised spectral–spatial feature learning. Moreover, this paper also introduces an in-depth investigation of learned features. Experimental results on two widely used hyperspectral data, Indian Pines and Pavia University, demonstrate competitive performance obtained by the proposed methodology compared with other studied approaches.

elib-URL des Eintrags:https://elib.dlr.de/114209/
Dokumentart:Zeitschriftenbeitrag
Titel:Unsupervised Spectral-Spatial Feature Learning via Deep Residual Conv-Deconv Network for Hyperspectral Image Classification
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Mou, Lichaolichao.mou (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Ghamisi, Pedrampedram.ghamisi (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Zhu, Xiao Xiangxiao.zhu (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:Januar 2018
Erschienen in:IEEE Transactions on Geoscience and Remote Sensing
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
Band:56
DOI:10.1109/TGRS.2017.2748160
Seitenbereich:Seiten 391-406
Verlag:IEEE - Institute of Electrical and Electronics Engineers
ISSN:0196-2892
Status:veröffentlicht
Stichwörter:Convolutional network, deconvolutional network, hyperspectral image classification, residual learning, unsupervised spectral-spatial feature learning
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Erdbeobachtung
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R EO - Erdbeobachtung
DLR - Teilgebiet (Projekt, Vorhaben):R - Vorhaben hochauflösende Fernerkundungsverfahren (alt)
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Methodik der Fernerkundung > SAR-Signalverarbeitung
Hinterlegt von: Mou, LiChao
Hinterlegt am:19 Sep 2017 11:42
Letzte Änderung:08 Nov 2023 14:42

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.