Repository logo
 
Publication

Data-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networks

2020Journal article Open access
Simple item page
dc.contributor.authorBen Jdira, Bilel
dc.contributor.authorAmmar, Adel
dc.contributor.authorKoubaa, Anis
dc.contributor.authorOuni, Kaïs
dc.date.accessioned2020-02-19T14:33:13Z
dc.date.available2020-02-19T14:33:13Z
dc.date.issued2020
dc.description.abstractDespite the significant advances noted in semantic segmentation of aerial imagery, a considerable limitation is blocking its adoption in real cases. If we test a segmentation model on a new area that is not included in its initial training set, accuracy will decrease remarkably. This is caused by the domain shift between the new targeted domain and the source domain used to train the model. In this paper, we addressed this challenge and proposed a new algorithm that uses Generative Adversarial Networks (GAN) architecture to minimize the domain shift and increase the ability of the model to work on new targeted domains. The proposed GAN architecture contains two GAN networks. The first GAN network converts the chosen image from the target domain into a semantic label. The second GAN network converts this generated semantic label into an image that belongs to the source domain but conserves the semantic map of the target image. This resulting image will be used by the semantic segmentation model to generate a better semantic label of the first chosen image. Our algorithm is tested on the ISPRS semantic segmentation dataset and improved the global accuracy by a margin up to 24% when passing from Potsdam domain to Vaihingen domain. This margin can be increased by addition of other labeled data from the target domain. To minimize the cost of supervision in the translation process, we proposed a methodology to use these labeled data efficiently.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.3390/app10031092pt_PT
dc.identifier.issn2076-3417
dc.identifier.urihttp://hdl.handle.net/10400.22/15490
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherMDPIpt_PT
dc.relation.publisherversionhttps://www.mdpi.com/2076-3417/10/3/1092/htmpt_PT
dc.subjectDeep learningpt_PT
dc.subjectSemantic segmentationpt_PT
dc.subjectGenerative adversarial networkspt_PT
dc.subjectConvolutional neural networkspt_PT
dc.subjectAerial imagerypt_PT
dc.titleData-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networkspt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage24pt_PT
oaire.citation.issue3pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleApplied Sciencespt_PT
oaire.citation.volume10pt_PT
person.familyNameBen Jdira
person.familyNameAmmar
person.familyNameKoubaa
person.familyNameOuni
person.givenNameBilel
person.givenNameAdel
person.givenNameAnis
person.givenNameKaïs
person.identifier989131
person.identifier.ciencia-idCA19-2399-D94A
person.identifier.orcid0000-0002-3057-4924
person.identifier.orcid0000-0003-0795-132X
person.identifier.orcid0000-0003-3787-7423
person.identifier.orcid0000-0003-1989-5177
person.identifier.scopus-author-id15923354900
person.identifier.scopus-author-id6505828746
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication419b97f7-4b56-412c-83b6-fc43cfb1848b
relation.isAuthorOfPublicationc6587bf7-dc30-4e11-8ade-36d17faafaf9
relation.isAuthorOfPublication0337d7df-5f77-46a4-8269-83d14bd5ea6b
relation.isAuthorOfPublicationbc3f6850-8c24-4ddc-8ca3-e2e5cb3638cc
relation.isAuthorOfPublication.latestForDiscoverybc3f6850-8c24-4ddc-8ca3-e2e5cb3638cc

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ART_CISTER_applsci_2020.pdf
Size:
1.92 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ISEP – CISTER – Artigos