LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, Inkyu | - |
dc.contributor.author | Kim, Dong Jin | - |
dc.contributor.author | Cho, Jae Won | - |
dc.contributor.author | Woo, Sanghyun | - |
dc.contributor.author | Park, Kwanyong | - |
dc.contributor.author | Kweon, In So | - |
dc.date.accessioned | 2023-09-11T01:50:23Z | - |
dc.date.available | 2023-09-11T01:50:23Z | - |
dc.date.created | 2023-07-21 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.issn | 15505499 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190363 | - |
dc.description.abstract | Unsupervised Domain Adaptation (UDA) for semantic segmentation has been actively studied to mitigate the domain gap between label-rich source data and unlabeled target data. Despite these efforts, UDA still has a long way to go to reach the fully supervised performance. To this end, we propose a Labeling Only if Required strategy, LabOR, where we introduce a human-in-the-loop approach to adaptively give scarce labels to points that a UDA model is uncertain about. In order to find the uncertain points, we generate an inconsistency mask using the proposed adaptive pixel selector and we label these segment-based regions to achieve near supervised performance with only a small fraction (about 2.2%) ground truth points, which we call "Segment based Pixel-Labeling (SPL)." To further reduce the efforts of the human annotator, we also propose "Point based Pixel-Labeling (PPL)," which finds the most representative points for labeling within the generated inconsistency mask. This reduces efforts from 2.2% segment label -> 40 points label while minimizing performance degradation. Through extensive experimentation, we show the advantages of this new framework for domain adaptive semantic segmentation while minimizing human labor costs. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE computer society & The computer vision foundation (CVF) | - |
dc.title | LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Dong Jin | - |
dc.identifier.doi | 10.1109/ICCV48922.2021.00847 | - |
dc.identifier.scopusid | 2-s2.0-85112499673 | - |
dc.identifier.wosid | 000798743207031 | - |
dc.identifier.bibliographicCitation | 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), pp.8568 - 8578 | - |
dc.relation.isPartOf | 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) | - |
dc.citation.title | 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) | - |
dc.citation.startPage | 8568 | - |
dc.citation.endPage | 8578 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9710745/authors#authors | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.