HD Maps are Lane Detection Generalizers: A Novel Generative Framework for Single-Source Domain Generalization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Daeun, Heo, Minhyeok, Kim, Jiwon
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916268437667840
author Lee, Daeun
Heo, Minhyeok
Kim, Jiwon
author_facet Lee, Daeun
Heo, Minhyeok
Kim, Jiwon
contents Lane detection is a vital task for vehicles to navigate and localize their position on the road. To ensure reliable driving, lane detection models must have robust generalization performance in various road environments. However, despite the advanced performance in the trained domain, their generalization performance still falls short of expectations due to the domain discrepancy. To bridge this gap, we propose a novel generative framework using HD Maps for Single-Source Domain Generalization (SSDG) in lane detection. We first generate numerous front-view images from lane markings of HD Maps. Next, we strategically select a core subset among the generated images using (i) lane structure and (ii) road surrounding criteria to maximize their diversity. In the end, utilizing this core set, we train lane detection models to boost their generalization performance. We validate that our generative framework from HD Maps outperforms the Domain Adaptation model MLDA with +3.01%p accuracy improvement, even though we do not access the target domain images.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16589
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HD Maps are Lane Detection Generalizers: A Novel Generative Framework for Single-Source Domain Generalization
Lee, Daeun
Heo, Minhyeok
Kim, Jiwon
Computer Vision and Pattern Recognition
Machine Learning
Robotics
Lane detection is a vital task for vehicles to navigate and localize their position on the road. To ensure reliable driving, lane detection models must have robust generalization performance in various road environments. However, despite the advanced performance in the trained domain, their generalization performance still falls short of expectations due to the domain discrepancy. To bridge this gap, we propose a novel generative framework using HD Maps for Single-Source Domain Generalization (SSDG) in lane detection. We first generate numerous front-view images from lane markings of HD Maps. Next, we strategically select a core subset among the generated images using (i) lane structure and (ii) road surrounding criteria to maximize their diversity. In the end, utilizing this core set, we train lane detection models to boost their generalization performance. We validate that our generative framework from HD Maps outperforms the Domain Adaptation model MLDA with +3.01%p accuracy improvement, even though we do not access the target domain images.
title HD Maps are Lane Detection Generalizers: A Novel Generative Framework for Single-Source Domain Generalization
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2311.16589