Domain-Incremental Semantic Segmentation for Autonomous Driving Under Adverse Driving Conditions

Shishir Muralidhara, Shishir Muralidhara, René Schuster, René Schuster, Didier Stricker, Didier Stricker

2025

Abstract

Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal conditions show a deteriorated performance in unfavorable weather or illumination conditions. Fine-tuning on the new task or condition would lead to overwriting the previously learned information resulting in catastrophic forgetting. Adapting to the new conditions through traditional domain adaption methods improves the performance on the target domain at the expense of the source domain. Addressing these issues, we propose an architecture-based domain-incremental learning approach called Progressive Semantic Segmentation (PSS). PSS is a task-agnostic, dynamically growing collection of domain-specific segmentation models. The task of inferring the domain and subsequently selecting the appropriate module for segmentation is carried out using a collection of convolutional autoencoders. We extensively evaluate our proposed approach using several datasets at varying levels of granularity in the categorization of adverse driving conditions. Furthermore, we demonstrate the generalization of the proposed approach to similar and unseen domains.

Paper Citation

in Harvard Style

Muralidhara S., Schuster R. and Stricker D. (2025). Domain-Incremental Semantic Segmentation for Autonomous Driving Under Adverse Driving Conditions. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 496-506. DOI: 10.5220/0013249100003905

in Bibtex Style

@conference{icpram25,
author={Shishir Muralidhara and René Schuster and Didier Stricker},
title={Domain-Incremental Semantic Segmentation for Autonomous Driving Under Adverse Driving Conditions},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={496-506},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013249100003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Domain-Incremental Semantic Segmentation for Autonomous Driving Under Adverse Driving Conditions
SN - 978-989-758-730-6
AU - Muralidhara S.
AU - Schuster R.
AU - Stricker D.
PY - 2025
SP - 496
EP - 506
DO - 10.5220/0013249100003905
PB - SciTePress