Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions

Alonso, Iñigo (Universidad de Zaragoza) ; Riazuelo, Luis (Universidad de Zaragoza) ; Montesano, Luis (Universidad de Zaragoza) ; Murillo, Ana Cristina (Universidad de Zaragoza)
Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions
Resumen: LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems, such as autonomous vehicles, during their decision making processes. Unfortunately, the annotation process for this task is very expensive. To overcome this, it is key to find models that generalize well or adapt to additional domains where labeled data is limited. This work addresses the problem of unsupervised domain adaptation for LiDAR semantic segmentation models. We propose simple but effective strategies to reduce the domain shift by aligning the data distribution on the input space. Besides, we present a learning-based module to align the distribution of the semantic classes of the target domain to the source domain. Our approach achieves new state-of-the-art results on three different public datasets, which showcase adaptation to three different domains.
Idioma: Inglés
DOI: 10.5220/0010610703300337
Año: 2021
Publicado en: Proceedings (International Asia Conference on Informatics in Control, Automation, and Robotics) 18 (2021), 330-337
ISSN: 1948-3414

Tipo y forma: Article (Published version)
Área (Departamento): Área Ingen.Sistemas y Automát. (Dpto. Informát.Ingenie.Sistms.)
Área (Departamento): Área Lenguajes y Sistemas Inf. (Dpto. Informát.Ingenie.Sistms.)

Exportado de SIDERAL (2022-05-19-11:22:23)


Visitas y descargas

Este artículo se encuentra en las siguientes colecciones:
articulos



 Notice créée le 2021-11-15, modifiée le 2022-05-19


Versión publicada:
 PDF
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)