Hua, Yuansheng und Mou, LiChao und Zhu, Xiao Xiang (2019) Multi-label Aerial Image Classification using A Bidirectional Class-wise Attention Network. In: 2019 Joint Urban Remote Sensing Event, JURSE 2019, Seiten 1-4. JURSE 2019, 2019-05-22 - 2019-05-24, Vannes, France. doi: 10.1109/JURSE.2019.8808940. ISBN 978-172810009-8.
![]() |
PDF
2MB |
Offizielle URL: https://ieeexplore.ieee.org/document/8808940
Kurzfassung
Multi-label aerial image classification is of great significance in remote sensing community, and many researches have been conducted over the past few years. However, one common limitation shared by existing methods is that the co-occurrence relationship of various classes, so called class dependency, is underexplored and leads to an inconsiderate decision. In this paper, we propose a novel end-to-end network, namely class-wise attention-based convolutional and bidirectional LSTM network (CA-Conv-BiLSTM), for this task. The proposed network consists of three indispensable components: 1) a feature extraction module, 2) a class attention learning layer, and 3) a bidirectional LSTM-based sub-network. Experimental results on UCM multi-label dataset and DFC15 multi-label dataset validate the effectiveness of our model quantitatively and qualitatively.
elib-URL des Eintrags: | https://elib.dlr.de/134068/ | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||||||
Titel: | Multi-label Aerial Image Classification using A Bidirectional Class-wise Attention Network | ||||||||||||||||
Autoren: |
| ||||||||||||||||
Datum: | Mai 2019 | ||||||||||||||||
Erschienen in: | 2019 Joint Urban Remote Sensing Event, JURSE 2019 | ||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||
Open Access: | Ja | ||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||
DOI: | 10.1109/JURSE.2019.8808940 | ||||||||||||||||
Seitenbereich: | Seiten 1-4 | ||||||||||||||||
Herausgeber: |
| ||||||||||||||||
ISBN: | 978-172810009-8 | ||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||
Stichwörter: | multi-label classification, high resolution aerial image, Convolutional Neural Network (CNN), class attention learning, Bidirectional Long Short-Term Memory (BiLSTM), class dependency | ||||||||||||||||
Veranstaltungstitel: | JURSE 2019 | ||||||||||||||||
Veranstaltungsort: | Vannes, France | ||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||
Veranstaltungsbeginn: | 22 Mai 2019 | ||||||||||||||||
Veranstaltungsende: | 24 Mai 2019 | ||||||||||||||||
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 > EO Data Science | ||||||||||||||||
Hinterlegt von: | Haschberger, Dr.-Ing. Peter | ||||||||||||||||
Hinterlegt am: | 11 Feb 2020 09:45 | ||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:37 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags