Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking
Most of the existing domain adaptation (DA) methods proposed in the context of remote sensing imagery assume the presence of the same land-cover classes in the source and target domains. Yet, this assumption is not always realistic in practice as the target domain may contain additional classes unkn...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/11/1716 |
id |
doaj-dbfb78a26f894f889baf1729fe4ba836 |
---|---|
record_format |
Article |
spelling |
doaj-dbfb78a26f894f889baf1729fe4ba8362020-11-25T03:10:41ZengMDPI AGRemote Sensing2072-42922020-05-01121716171610.3390/rs12111716Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto RankingReham Adayel0Yakoub Bazi1Haikel Alhichri2Naif Alajlan3Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaComputer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaComputer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaComputer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi ArabiaMost of the existing domain adaptation (DA) methods proposed in the context of remote sensing imagery assume the presence of the same land-cover classes in the source and target domains. Yet, this assumption is not always realistic in practice as the target domain may contain additional classes unknown to the source leading to the so-called open set DA. Under this challenging setting, the problem turns to reducing the distribution discrepancy between the shared classes in both domains besides the detection of the unknown class samples in the target domain. To deal with the openset problem, we propose an approach based on adversarial learning and pareto-based ranking. In particular, the method leverages the distribution discrepancy between the source and target domains using min-max entropy optimization. During the alignment process, it identifies candidate samples of the unknown class from the target domain through a pareto-based ranking scheme that uses ambiguity criteria based on entropy and the distance to source class porotypes. Promising results using two cross-domain datasets that consist of very high resolution and extremely high resolution images, show the effectiveness of the proposed method.https://www.mdpi.com/2072-4292/12/11/1716scene classificationopen-set domain adaptationadversarial learningmin-max entropypareto ranking. |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Reham Adayel Yakoub Bazi Haikel Alhichri Naif Alajlan |
spellingShingle |
Reham Adayel Yakoub Bazi Haikel Alhichri Naif Alajlan Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking Remote Sensing scene classification open-set domain adaptation adversarial learning min-max entropy pareto ranking. |
author_facet |
Reham Adayel Yakoub Bazi Haikel Alhichri Naif Alajlan |
author_sort |
Reham Adayel |
title |
Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking |
title_short |
Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking |
title_full |
Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking |
title_fullStr |
Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking |
title_full_unstemmed |
Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking |
title_sort |
deep open-set domain adaptation for cross-scene classification based on adversarial learning and pareto ranking |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-05-01 |
description |
Most of the existing domain adaptation (DA) methods proposed in the context of remote sensing imagery assume the presence of the same land-cover classes in the source and target domains. Yet, this assumption is not always realistic in practice as the target domain may contain additional classes unknown to the source leading to the so-called open set DA. Under this challenging setting, the problem turns to reducing the distribution discrepancy between the shared classes in both domains besides the detection of the unknown class samples in the target domain. To deal with the openset problem, we propose an approach based on adversarial learning and pareto-based ranking. In particular, the method leverages the distribution discrepancy between the source and target domains using min-max entropy optimization. During the alignment process, it identifies candidate samples of the unknown class from the target domain through a pareto-based ranking scheme that uses ambiguity criteria based on entropy and the distance to source class porotypes. Promising results using two cross-domain datasets that consist of very high resolution and extremely high resolution images, show the effectiveness of the proposed method. |
topic |
scene classification open-set domain adaptation adversarial learning min-max entropy pareto ranking. |
url |
https://www.mdpi.com/2072-4292/12/11/1716 |
work_keys_str_mv |
AT rehamadayel deepopensetdomainadaptationforcrosssceneclassificationbasedonadversariallearningandparetoranking AT yakoubbazi deepopensetdomainadaptationforcrosssceneclassificationbasedonadversariallearningandparetoranking AT haikelalhichri deepopensetdomainadaptationforcrosssceneclassificationbasedonadversariallearningandparetoranking AT naifalajlan deepopensetdomainadaptationforcrosssceneclassificationbasedonadversariallearningandparetoranking |
_version_ |
1724658001378279424 |