Multi-source Domain Adaptation for Unsupervised Road Defect Segmentation

Yu, Jongmin, Oh, Hyeontaek, Fichera, Sebastiano ORCID: 0000-0003-1006-4959, Paoletti, Paolo ORCID: 0000-0001-6131-0377 and Luo, Shan (2023) Multi-source Domain Adaptation for Unsupervised Road Defect Segmentation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023-5-29 - 2023-6-2.

Text
ICRA2023_Road_defect_segmentation_MDA.pdf - Author Accepted Manuscript
Download (1MB) | Preview

Official URL: http://dx.doi.org/10.1109/icra48891.2023.10161099

Abstract

The performance of road defect segmentation (a.k.a. pixel-level road defect detection) has been improved alongside with remarkable achievement of deep learning. Those improvements need a large-scale and well-constructed dataset. However, road surface materials or designs vary from country to country, and the patterns of defects are hard to pre-define. In this paper, we propose a novel multi-source domain adaptation method to boost the performance of road defect segmentation on an unlabelled dataset. The proposed method generates multi-source ensembled labels using transferred information from models trained with multiple labelled source domains, which are utilised as supervisory signals for the unlabelled target domain. Furthermore, to reduce the domain gap between each source domain and a target domain, these domains are re-aligned with outlier repositioning to improve the defect segmentation performance. We demonstrate the effectiveness of our proposed method on Cracktree200, CRACK500, CFD, and Crack360 datasets. Experimental results show that the proposed method outperforms the existing unsupervised road defect segmentation methods and achieves competitive performance compared with recent supervised methods. The source code is publicly available on https://github.com/andreYoo/MSDA_RDS.git.

Item Type:	Conference or Workshop Item (Unspecified)
Uncontrolled Keywords:	3 Good Health and Well Being
Divisions:	Faculty of Science and Engineering > School of Engineering
Depositing User:	Symplectic Admin
Date Deposited:	13 Mar 2023 08:41
Last Modified:	15 Mar 2024 06:50
DOI:	10.1109/icra48891.2023.10161099
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3168945