Header

UZH-Logo

Maintenance Infos

Semisupervised transfer component analysis for domain adaptation in remote sensing image classification


Matasci, Giona; Volpi, Michele; Kanevski, Mikhail; Bruzzone, Lorenzo; Tuia, Devis (2015). Semisupervised transfer component analysis for domain adaptation in remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 53(7):3550-3564.

Abstract

In this paper, we study the problem of feature extraction for knowledge transfer between multiple remotely sensed images in the context of land-cover classification. Several factors such as illumination, atmospheric, and ground conditions cause radiometric differences between images of similar scenes acquired on different geographical areas or over the same scene but at different time instants. Accordingly, a change in the probability distributions of the classes is observed. The purpose of this work is to statistically align in the feature space an image of interest that still has to be classified (the target image) to another image whose ground truth is already available (the source image). Following a specifically designed feature extraction step applied to both images, we show that classifiers trained on the source image can successfully predict the classes of the target image despite the shift that has occurred. In this context, we analyze a recently proposed domain adaptation method aiming at reducing the distance between domains, Transfer Component Analysis, and assess the potential of its unsupervised and semisupervised implementations. In particular, with a dedicated study of its key additional objectives, namely the alignment of the projection with the labels and the preservation of the local data structures, we demonstrate the advantages of Semisupervised Transfer Component Analysis. We compare this approach with other both linear and kernel-based feature extraction techniques. Experiments on multi- and hyperspectral acquisitions show remarkable crossimage classification performances for the considered strategy, thus confirming its suitability when applied to remotely sensed images.

Abstract

In this paper, we study the problem of feature extraction for knowledge transfer between multiple remotely sensed images in the context of land-cover classification. Several factors such as illumination, atmospheric, and ground conditions cause radiometric differences between images of similar scenes acquired on different geographical areas or over the same scene but at different time instants. Accordingly, a change in the probability distributions of the classes is observed. The purpose of this work is to statistically align in the feature space an image of interest that still has to be classified (the target image) to another image whose ground truth is already available (the source image). Following a specifically designed feature extraction step applied to both images, we show that classifiers trained on the source image can successfully predict the classes of the target image despite the shift that has occurred. In this context, we analyze a recently proposed domain adaptation method aiming at reducing the distance between domains, Transfer Component Analysis, and assess the potential of its unsupervised and semisupervised implementations. In particular, with a dedicated study of its key additional objectives, namely the alignment of the projection with the labels and the preservation of the local data structures, we demonstrate the advantages of Semisupervised Transfer Component Analysis. We compare this approach with other both linear and kernel-based feature extraction techniques. Experiments on multi- and hyperspectral acquisitions show remarkable crossimage classification performances for the considered strategy, thus confirming its suitability when applied to remotely sensed images.

Statistics

Citations

Dimensions.ai Metrics
34 citations in Web of Science®
33 citations in Scopus®
32 citations in Microsoft Academic
Google Scholar™

Altmetrics

Downloads

0 downloads since deposited on 23 Dec 2015
0 downloads since 12 months

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:570 Life sciences; biology
590 Animals (Zoology)
Language:English
Date:2015
Deposited On:23 Dec 2015 10:03
Last Modified:14 Feb 2018 10:16
Publisher:Institute of Electrical and Electronics Engineers
ISSN:0196-2892
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/tgrs.2014.2377785

Download