Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/157049
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHuang, Jiaxingen_US
dc.contributor.authorGuan, Dayanen_US
dc.contributor.authorXiao, Aoranen_US
dc.contributor.authorLu, Shijianen_US
dc.date.accessioned2022-05-01T06:16:55Z-
dc.date.available2022-05-01T06:16:55Z-
dc.date.issued2022-
dc.identifier.citationHuang, J., Guan, D., Xiao, A. & Lu, S. (2022). Multi-level adversarial network for domain adaptive semantic segmentation. Pattern Recognition, 123, 108384-. https://dx.doi.org/10.1016/j.patcog.2021.108384en_US
dc.identifier.issn0031-3203en_US
dc.identifier.urihttps://hdl.handle.net/10356/157049-
dc.description.abstractRecent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions at a global image level but neglect the inconsistency around local image regions. This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. MLAN has two novel designs, namely, region-level adversarial learning (RL-AL) and co-regularized adversarial learning (CR-AL). Specifically, RL-AL models prototypical regional context-relations explicitly in the feature space of a labelled source domain and transfers them to an unlabelled target domain via adversarial learning. CR-AL fuses region-level AL and image-level AL optimally via mutual regularization. In addition, we design a multi-level consistency map that can guide domain adaptation in both input space (i.e., image-to-image translation) and output space (i.e., self-training) effectively. Extensive experiments show that MLAN outperforms the state-of-the-art with a large margin consistently across multiple datasets.en_US
dc.language.isoenen_US
dc.relation.ispartofPattern Recognitionen_US
dc.rights© 2021 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.titleMulti-level adversarial network for domain adaptive semantic segmentationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.identifier.doi10.1016/j.patcog.2021.108384-
dc.description.versionSubmitted/Accepted versionen_US
dc.identifier.scopus2-s2.0-85118151273-
dc.identifier.volume123en_US
dc.identifier.spage108384en_US
dc.subject.keywordsUnsupervised Domain Adaptationen_US
dc.subject.keywordsSemantic Segmentationen_US
item.fulltextWith Fulltext-
item.grantfulltextembargo_20240407-
Appears in Collections:SCSE Journal Articles
Files in This Item:
File Description SizeFormat 
Multi-level adversarial network for domain adaptive semantic segmentation.pdf
  Until 2024-04-07
3.52 MBAdobe PDFUnder embargo until Apr 07, 2024

Page view(s)

29
Updated on Jul 5, 2022

Google ScholarTM

Check

Altmetric


Plumx

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