Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation
Sur, Tanuj Mukherjee, Samrat Rahaman, Kaizer Chaudhuri, Subhasis Khan, Muhammad Haris Banerjee, Biplab
Sur, Tanuj
Mukherjee, Samrat
Rahaman, Kaizer
Chaudhuri, Subhasis
Khan, Muhammad Haris
Banerjee, Biplab
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
3D point cloud segmentation is essential across a range of applications; however, conventional methods often struggle in evolving environments, particularly when tasked with identifying novel categories under limited supervision. Few-Shot Learning (FSL) and Class Incremental Learning (CIL) have been adapted previously to address these challenges in isolation, yet the combined paradigm of Few-Shot Class Incremental Learning (FSCIL) remains largely unexplored for point cloud segmentation. To address this gap, we introduce Hyperbolic Ideal Prototypes Optimization (HIPO), a novel framework that harnesses hyperbolic embeddings for FSCIL in 3D point clouds. HIPO employs the Poincare Hyperbolic Sphere as its embedding space, integrating Ideal Prototypes enriched by CLIP-derived class semantics, to capture the hierarchical structure of 3D data. By enforcing orthogonality among prototypes and maximizing representational margins, HIPO constructs a resilient embedding space that mitigates forgetting and enables the seamless integration of new classes, thereby effectively countering overfitting. Extensive evaluations on S3DIS, ScanNetv2, and cross-dataset scenarios demonstrate HIPO's strong performance, significantly surpassing existing approaches in both in-domain and cross-dataset FSCIL tasks for 3D point cloud segmentation.
Citation
T. Sur, S. Mukherjee, K. Rahaman, S. Chaudhuri, M. H. Khan, and B. Banerjee, “Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation,” 2025.
Source
Proceedings of the Computer Vision and Pattern Recognition Conference
Conference
Computer Vision and Pattern Recognition Conference (CVPR), 2025
Keywords
Subjects
Source
Computer Vision and Pattern Recognition Conference (CVPR), 2025
Publisher
Computer Vision Foundation