LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentationopen access
- Authors
- Shin, Inkyu; Kim, Dong Jin; Cho, Jae Won; Woo, Sanghyun; Park, Kwanyong; Kweon, In So
- Issue Date
- Oct-2021
- Publisher
- IEEE computer society & The computer vision foundation (CVF)
- Citation
- 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), pp.8568 - 8578
- Indexed
- SCOPUS
- Journal Title
- 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
- Start Page
- 8568
- End Page
- 8578
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190363
- DOI
- 10.1109/ICCV48922.2021.00847
- ISSN
- 15505499
- 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.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/190363)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.