Lei Wang

CGRD: An Exemplar-Free Extension of Knowledge Distillation for Class-Incremental 3D Point Cloud Semantic Segmentation

Confidence-gated relational distillation is proposed, an exemplar-free teacher–student framework that combines feature-level relation preservation with semantic-level background correction that provides an effective balance between old-class retention and novel-class acquisition without introducing replay data or separate architectural branches during incremental optimization.