EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Reliability-Guided Unsupervised Domain Adaptation Framework for Robust Semantic Segmentation Under Adverse Driving Conditions

Nan Xia, Guoqing Hu

Applied Sciences · 20.03.2026 · 16 (6) · 3036

DOI: 10.3390/app16063036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 20.03.2026. Verfasst von Nan Xia und 1 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chinese 863 projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adverse weather and low illumination remain major challenges for autonomous driving perception, where semantic segmentation must stay reliable despite severe appearance degradation. In unsupervised domain adaptation without target annotations, self-training is widely used, but it is often limited by the inconsistent quality of teacher-generated pseudo labels across samples, regions, and training stages. This paper presents RaDA, a reliability-aware self-training framework that regulates pseudo supervision at three levels. First, a progressive exposure strategy determines which target images are admitted for training. Second, spatial reliability weighting suppresses gradients from degraded regions while retaining informative supervision. Third, adaptive teacher update scheduling stabilizes pseudo label generation over time. Experiments on real-world adverse driving benchmarks show that RaDA improves robustness, training stability, and cross-dataset generalization compared with strong baselines. Compared with the previous state-of-the-art method MIC, RaDA achieves mIoU gains of 10.6 percentage points on Foggy Zurich and 8.8 percentage points on the Foggy Driving benchmark. These results indicate that explicit reliability regulation can strengthen self-training domain adaptation for semantic segmentation in autonomous driving under challenging environmental conditions.

Förderung

  • Chinese 863 projects

Zitieren

APA

Xia, N., & Hu, G. (2026). A Reliability-Guided Unsupervised Domain Adaptation Framework for Robust Semantic Segmentation Under Adverse Driving Conditions. Applied Sciences, 16(6), 3036. https://doi.org/10.3390/app16063036

Vancouver

Xia N, Hu G. A Reliability-Guided Unsupervised Domain Adaptation Framework for Robust Semantic Segmentation Under Adverse Driving Conditions. Applied Sciences. 2026;16(6):3036. doi:10.3390/app16063036

BibTeX
@article{Xia2026,
  author = {Xia, Nan and Hu, Guoqing},
  title = {A Reliability-Guided Unsupervised Domain Adaptation Framework for Robust Semantic Segmentation Under Adverse Driving Conditions},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {3036},
  doi = {10.3390/app16063036}
}
Kostenlos starten →