Learning a multi-branch neural network from multiple sources for knowledge adaptation in remote sensing imagery

Al Rahhal, M. M. and Bazi, Yakoub and Abdullah, Taghreed and Mekhalfi, M. L. and AlHichri, Haikel and Zuair, Mansour (2018) Learning a multi-branch neural network from multiple sources for knowledge adaptation in remote sensing imagery. Remote Sensing, 10 (12). p. 1890. ISSN 2072-4292

Text (Full Text) Learning multi-brach neural network.pdf - Published Version Download (7MB)

Abstract

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.

Item Type:	Article
Subjects:	D Physical Science > Computer Science
Divisions:	Department of > Computer Science
Depositing User:	Manjula P Library Assistant
Date Deposited:	17 Jul 2019 07:26
Last Modified:	22 Jun 2022 09:12
URI:	http://eprints.uni-mysore.ac.in/id/eprint/5311

Actions (login required)

View Item