Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hilaire, Christian, Didari, Sima
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.13043
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912432137437184
author Hilaire, Christian
Didari, Sima
author_facet Hilaire, Christian
Didari, Sima
contents We propose a novel active learning framework for multi-view semantic segmentation. This framework relies on a new score that measures the discrepancy between point cloud distributions generated from the extra geometrical information derived from the model's prediction across different views. Our approach results in a data efficient and explainable active learning method. The source code is available at https://github.com/chilai235/viewpclAL.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ViewPCL: a point cloud based active learning method for multi-view segmentation
Hilaire, Christian
Didari, Sima
Computer Vision and Pattern Recognition
We propose a novel active learning framework for multi-view semantic segmentation. This framework relies on a new score that measures the discrepancy between point cloud distributions generated from the extra geometrical information derived from the model's prediction across different views. Our approach results in a data efficient and explainable active learning method. The source code is available at https://github.com/chilai235/viewpclAL.
title ViewPCL: a point cloud based active learning method for multi-view segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.13043