Few-shot Learning/3D Segmentation1 [논문리뷰]Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model Paper OverviewCVPR'25https://arxiv.org/abs/2503.16282 Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language ModelGeneralized few-shot 3D point cloud segmentation (GFS-PCS) adapts models to new classes with few support samples while retaining base class segmentation. Existing GFS-PCS methods enhance prototypes via interacting with support or query features but remainarxiv.org Abst.. 2025. 5. 2. 이전 1 다음