Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 05. Juli
1. Verfasser: Wu, Yizheng (VerfasserIn)
Weitere Verfasser: Pan, Zhiyu, Wang, Kewei, Li, Xingyi, Cui, Jiahao, Xiao, Liwen, Lin, Guosheng, Cao, Zhiguo
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article