2024
TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation
IROS 2024
In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle’s surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the limitations of current few-shot semantic segmentation by exploiting