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

Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification

Hua, Yuansheng and Mou, LiChao and Zhu, Xiao Xiang (2019) Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification. ISPRS Journal of Photogrammetry and Remote Sensing, 149, pp. 188-199. Elsevier. DOI: 10.1016/j.isprsjprs.2019.01.015 ISSN 0924-2716

[img] PDF
16MB

Official URL: https://authors.elsevier.com/c/1YWFC3I9x1YrkJ

Abstract

Aerial image classification is of great significance in the remote sensing community, and many researches have been conducted over the past few years. Among these studies, most of them focus on categorizing an image into one semantic label, while in the real world, an aerial image is often associated with multiple labels, e.g., multiple object-level labels in our case. Besides, a comprehensive picture of present objects in a given high-resolution aerial image can provide a more in-depth understanding of the studied region. For these reasons, aerial image multi-label classification has been attracting increasing attention. However, one common limitation shared by existing methods in the community 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. Particularly, the feature extraction module is designed for extracting fine-grained semantic feature maps, while the class attention learning layer aims at capturing discriminative class-specific features. As the most important part, the bidirectional LSTM-based sub-network models the underlying class dependency in both directions and produce structured multiple object labels. Experimental results on UCM multi-label dataset and DFC15 multi-label dataset validate the effectiveness of our model quantitatively and qualitatively.

Item URL in elib:https://elib.dlr.de/126414/
Document Type:Article
Title:Recurrently exploring class-wise attention in a hybrid convolutional and bidirectional LSTM network for multi-label aerial image classification
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Hua, YuanshengYuansheng.Hua (at) dlr.deUNSPECIFIED
Mou, LiChaoLiChao.Mou (at) dlr.deUNSPECIFIED
Zhu, Xiao Xiangxiaoxiang.zhu (at) dlr.deUNSPECIFIED
Date:March 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:149
DOI :10.1016/j.isprsjprs.2019.01.015
Page Range:pp. 188-199
Publisher:Elsevier
ISSN:0924-2716
Status:Published
Keywords:Multi-label classification High-resolution aerial image Convolutional Neural Network (CNN) l Class Attention Learning Bidirectional Long Short-Term Memory (BiLSTM) Class dependency
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 - Remote sensing and geoscience
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Hua, Yuansheng
Deposited On:07 Feb 2019 10:48
Last Modified:01 Mar 2020 03:00

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.