Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/157050
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGuan, Dayanen_US
dc.contributor.authorHuang, Jiaxingen_US
dc.contributor.authorLu, Shijianen_US
dc.contributor.authorXiao, Aoranen_US
dc.date.accessioned2022-05-01T06:34:41Z-
dc.date.available2022-05-01T06:34:41Z-
dc.date.issued2021-
dc.identifier.citationGuan, D., Huang, J., Lu, S. & Xiao, A. (2021). Scale variance minimization for unsupervised domain adaptation in image segmentation. Pattern Recognition, 112, 107764-. https://dx.doi.org/10.1016/j.patcog.2020.107764en_US
dc.identifier.issn0031-3203en_US
dc.identifier.urihttps://hdl.handle.net/10356/157050-
dc.description.abstractWe focus on unsupervised domain adaptation (UDA) in image segmentation. Existing works address this challenge largely by aligning inter-domain representations, which may lead over-alignment that impairs the semantic structures of images and further target-domain segmentation performance. We design a scale variance minimization (SVMin) method by enforcing the intra-image semantic structure consistency in the target domain. Specifically, SVMin leverages an intrinsic property that simple scale transformation has little effect on the semantic structures of images. It thus introduces certain supervision in the target domain by imposing a scale-invariance constraint while learning to segment an image and its scale-transformation concurrently. Additionally, SVMin is complementary to most existing UDA techniques and can be easily incorporated with consistent performance boost but little extra parameters. Extensive experiments show that our method achieves superior domain adaptive segmentation performance as compared with the state-of-the-art. Preliminary studies show that SVMin can be easily adapted for UDA-based image classification.en_US
dc.language.isoenen_US
dc.relation.ispartofPattern Recognitionen_US
dc.rights© 2020 Elsevier Ltd. All rights reserved. This paper was published in Pattern Recognition and is made available with permission of Elsevier Ltd.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleScale variance minimization for unsupervised domain adaptation in image segmentationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.researchSingtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU)en_US
dc.identifier.doi10.1016/j.patcog.2020.107764-
dc.description.versionSubmitted/Accepted versionen_US
dc.identifier.scopus2-s2.0-85097709318-
dc.identifier.volume112en_US
dc.identifier.spage107764en_US
dc.subject.keywordsUnsupervised Domain Adaptationen_US
dc.subject.keywordsImage Segmentationen_US
dc.description.acknowledgementThis research was conducted at Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU), which is a collaboration between Singapore Telecommunications Limited (Singtel) and Nanyang Technological University (NTU) that is funded by the Singapore Government through the Industry Alignment Fund - Industry Collaboration Projects Grant.en_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SCSE Journal Articles
Files in This Item:
File Description SizeFormat 
Scale variance minimization for unsupervised domain adaptation in image segmentation.pdf25.68 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 10

47
Updated on Mar 26, 2024

Web of ScienceTM
Citations 10

39
Updated on Oct 27, 2023

Page view(s)

129
Updated on Mar 28, 2024

Download(s) 50

34
Updated on Mar 28, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.