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...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Hui Ye, Wei Guo, Liang Ma, Xiangyi Shi, Jianqiang Ma
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2026-01-01
Schriftenreihe:	IEEE Access
Schlagworte:	3-D point cloud semi-supervised class-incremental segmentation multi-scale graph attention
Online-Zugang:	https://ieeexplore.ieee.org/document/11435883/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!