Next Article in Journal
Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds
Next Article in Special Issue
A Novel Deep Fully Convolutional Network for PolSAR Image Classification
Previous Article in Journal
Fully Connected Conditional Random Fields for High-Resolution Remote Sensing Land Use/Land Cover Classification with Convolutional Neural Networks
Previous Article in Special Issue
Ground and Multi-Class Classification of Airborne Laser Scanner Point Clouds Using Fully Convolutional Networks
Open AccessArticle

Learning a Multi-Branch Neural Network from Multiple Sources for Knowledge Adaptation in Remote Sensing Imagery

1
Information Science Department, College of Applied Computer Science, King Saud University, Riyadh 11543, Saudi Arabia
2
Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia
3
Department of Studies in Computer Science, University of Mysore, Mysore 570006, India
4
Department of Electronics, Faculty of Technology, University of Batna, Batna 05000, Algeria
*
Author to whom correspondence should be addressed.
Remote Sens. 2018, 10(12), 1890; https://doi.org/10.3390/rs10121890
Received: 3 October 2018 / Revised: 19 November 2018 / Accepted: 23 November 2018 / Published: 27 November 2018
(This article belongs to the Special Issue Recent Advances in Neural Networks for Remote Sensing)
In this paper we propose a multi-branch neural network, called MB-Net, for solving the problem of knowledge adaptation from multiple remote sensing scene datasets acquired with different sensors over diverse locations and manually labeled with different experts. Our aim is to learn invariant feature representations from multiple source domains with labeled images and one target domain with unlabeled images. To this end, we define for MB-Net an objective function that mitigates the multiple domain shifts at both feature representation and decision levels, while retaining the ability to discriminate between different land-cover classes. The complete architecture is trainable end-to-end via the backpropagation algorithm. In the experiments, we demonstrate the effectiveness of the proposed method on a new multiple domain dataset created from four heterogonous scene datasets well known to the remote sensing community, namely, the University of California (UC-Merced) dataset, the Aerial Image dataset (AID), the PatternNet dataset, and the Northwestern Polytechnical University (NWPU) dataset. In particular, this method boosts the average accuracy over all transfer scenarios up to 89.05% compared to standard architecture based only on cross-entropy loss, which yields an average accuracy of 78.53%. View Full-Text
Keywords: scene classification; multiple sources; multiple domain shifts; multi-branch neural network scene classification; multiple sources; multiple domain shifts; multi-branch neural network
Show Figures

Figure 1

MDPI and ACS Style

Al Rahhal, M.M.; Bazi, Y.; Abdullah, T.; Mekhalfi, M.L.; AlHichri, H.; Zuair, M. Learning a Multi-Branch Neural Network from Multiple Sources for Knowledge Adaptation in Remote Sensing Imagery. Remote Sens. 2018, 10, 1890.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop