Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art

Abstract

In this paper, we review the state of the art in Out-of-Distribution (OoD) segmentation, with a focus on road obstacle detection in automated driving as a real-world application. We analyse the performance of existing methods on two widely used benchmarks, SegmentMeIfYouCan Obstacle Track and LostAndFound-NoKnown, highlighting their strengths, limitations, and real-world applicability. Additionally, we discuss key challenges and outline potential research directions to advance the field. Our goal is to provide researchers and practitioners with a comprehensive perspective on the current landscape of OoD segmentation and to foster further advancements toward safer and more reliable autonomous driving systems.

Cite

Text

Shoeb et al. "Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.

Markdown

[Shoeb et al. "Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/shoeb2025cvprw-outofdistribution/)

BibTeX

@inproceedings{shoeb2025cvprw-outofdistribution,
  title     = {{Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Art}},
  author    = {Shoeb, Youssef and Nowzad, Azarm and Gottschalk, Hanno},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2025},
  pages     = {4310-4320},
  url       = {https://mlanthology.org/cvprw/2025/shoeb2025cvprw-outofdistribution/}
}