Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation

Samuel Marschall, Kira Maag

2025

Abstract

Deep neural networks have shown outstanding performance in computer vision tasks such as semantic segmentation and have defined the state-of-the-art. However, these segmentation models are trained on a closed and predefined set of semantic classes, which leads to significant prediction failures in open-world scenarios on unknown objects. As this behavior prevents the application in safety-critical applications such as automated driving, the detection and segmentation of these objects from outside their predefined semantic space (out-of-distribution (OOD) objects) is of the utmost importance. In this work, we present a multi-scale OOD segmentation method that exploits the confidence information of a foreground-background segmentation model. While semantic segmentation models are trained on specific classes, this restriction does not apply to foreground-background methods making them suitable for OOD segmentation. We consider the per pixel confidence score of the model prediction which is close to 1 for a pixel in a foreground object. By aggregating these confidence values for different sized patches, objects of various sizes can be identified in a single image. Our experiments show improved performance of our method in OOD segmentation compared to comparable baselines in the SegmentMeIfYouCan benchmark.

Paper Citation

in Harvard Style

Marschall S. and Maag K. (2025). Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 486-496. DOI: 10.5220/0013241800003912

in Bibtex Style

@conference{visapp25,
author={Samuel Marschall and Kira Maag},
title={Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={486-496},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013241800003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Multi-Scale Foreground-Background Confidence for Out-of-Distribution Segmentation
SN - 978-989-758-728-3
AU - Marschall S.
AU - Maag K.
PY - 2025
SP - 486
EP - 496
DO - 10.5220/0013241800003912
PB - SciTePress