[2603.19788] Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.19788 (cs) [Submitted on 20 Mar 2026] Title:Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation Authors:Yifei Zhao, Fanyu Zhao, Zhongyuan Zhang, Shengtang Wu, Yixuan Lin, Yinsheng Li View a PDF of the paper titled Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation, by Yifei Zhao and 5 other authors View PDF HTML (experimental) Abstract:Generalized few-shot 3D point cloud segmentation aims to adapt to novel classes from only a few annotations while maintaining strong performance on base classes, but this remains challenging due to the inherent stability-plasticity trade-off: adapting to novel classes can interfere with shared representations and cause base-class forgetting. We present HOP3D, a unified framework that learns hierarchical orthogonal prototypes with an entropy-based few-shot regularizer to enable robust novel-class adaptation without degrading base-class performance. HOP3D introduces hierarchical orthogonalization that decouples base and novel learning at both the gradient and representation levels, effectively mitigating base-novel interference. To further enhance adaptation under sparse supervision, we incorporate an entropy-based regularizer that leverages predictive uncertainty to refine prototype learning and promote balanced predictions. Extensive experiments on ScanNet200 and ScanNet++ demonstrat...