P3CL: Pseudo-Label Confidence-Calibrated Curriculum Learning for Weakly Supervised Urban Airborne Laser Scanning Point Cloud Classification

Urban airborne laser scanning (ALS) point clouds cover extensive geographical areas, rendering dense point-level annotation economically prohibitive and limiting the feasibility of fully supervised learning. In weakly supervised settings for urban ALS data, the natural long-tailed class distribution...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Ziwei Luo, Tao Zeng, Jun Jiang, Ziyang Cai, Wanru Wu, Zhong Xie, Yongyang Xu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-02-01
coleção:	Remote Sensing
Assuntos:	point cloud classification airborne laser scanning point clouds weakly supervised curriculum learning pseudo-label refinement
Acesso em linha:	https://www.mdpi.com/2072-4292/18/4/552
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!