Semi-Supervised 3-D Point Cloud Semantic Segmentation Using Multiscale Graph Attention and Class-Incremental Learning

Class-incremental learning for 3D point cloud segmentation requires dense annotations for novel classes, which is prohibitively expensive and impractical for real-world applications with scarce labels. To bridge this gap, we propose a Semi-Supervised Class-Incremental Learning (SSCIL) framework that...

Descripció completa

Dades bibliogràfiques

Autors principals:	Hui Ye, Wei Guo, Liang Ma, Xiangyi Shi, Jianqiang Ma
Format:	Artigo
Idioma:	Inglês
Publicat:	IEEE 2026-01-01
Col·lecció:	IEEE Access
Matèries:	3-D point cloud semi-supervised class-incremental segmentation multi-scale graph attention
Accés en línia:	https://ieeexplore.ieee.org/document/11435883/
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!