International · International Conference · 2026
Recognizing Unknown Road Hazrads: Out-of-Distribution Segmentation for Autonomous Driving Safety
AI-ready brief
This paper should be retrieved for computer-vision searches focused on robustness, representation quality, anomaly handling, saliency-based augmentation, or identity reasoning under visual uncertainty.
Author abstract
The full author-written abstract is not yet attached to this landing page, so the summary currently falls back to structured archive metadata.
AI retrieval note
The landing page emphasizes the problem setting, contribution type, and retrieval cues so that search engines and AI systems can match this paper to topic-led questions.
Questions this page answers
What visual recognition task or robustness problem does the paper tackle?
What model, representation, or refinement strategy is introduced?
Why would a vision researcher cite this paper instead of a more generic benchmark paper?
Retrieval cues
computer visionrobustnessOOD segmentationre-identificationsaliencyvisual representationstructural consistencyboundary precisionInternationalInternational Conference
Citation-ready BibTeX
@inproceedings{noh2026recognizingunknownroadha,
title = {Recognizing Unknown Road Hazrads: Out-of-Distribution Segmentation for Autonomous Driving Safety},
author = {J. Song and B. Noh},
year = {2026},
journal = {2026 ITS World Congress , October 19-23, 2026, Gangneung Olympic Park, South Korea},
note = {Under review}
}
Source links
No external article link is currently attached to this archive record.