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

• URL: http://arxiv.org/abs/2603.19788v1
• Date: Fri, 20 Mar 2026 09:23:34 GMT
• Title: Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation
• Abstract summary: 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.<n>We present HOP3D, a unified framework that learns hierarchical prototypes with an entropy-based few-shot regularizer.<n>Experiments on ScanNet200 and ScanNet++ demonstrate that HOP3D consistently outperforms state-of-the-art baselines.
• Score: 5.923682154394584
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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++ demonstrate that HOP3D consistently outperforms state-of-the-art baselines under both 1-shot and 5-shot settings. The code is available at https://fdueblab-hop3d.github.io/.

Related papers

• Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds [53.82500407523346]
  PointINS is an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.<n>PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation.
  arXiv  Detail & Related papers  (2026-03-26T08:31:06Z)
• SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation [51.48871964840347]
  SCOPE (Scene-COnised Prototype Enrichment) is a plug-and-play background-guided prototype enrichment framework.<n>It integrates with any prototype-based 3D segmentation method.<n>It achieves SOTA performance, improving novel-class IoU by up to 6.98% and 3.61%, and mean IoU by 2.25% and 1.70%, respectively.
  arXiv  Detail & Related papers  (2026-03-06T18:59:36Z)
• Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration [12.973924671425074]
  Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes.<n>A significant challenge with these models is their tendency to make biased predictions, often favoring the classes encountered during training.<n>We propose E3DPC-GZSL, which reduces overconfident predictions towards seen classes without relying on separate classifiers for seen and unseen data.
  arXiv  Detail & Related papers  (2025-09-10T04:37:00Z)
• Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification [59.68055837500357]
  We propose the first prototype-based framework named Proto-FG3D for fine-grained 3D shape classification.<n>Proto-FG3D establishes joint multi-view and multi-category representation learning via Prototype Association.<n>Proto-FG3D surpasses state-of-the-art methods in accuracy, transparent predictions, and ad-hoc interpretability with visualizations.
  arXiv  Detail & Related papers  (2025-05-23T09:31:02Z)
• ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation [9.578322021478426]
  offline-trained segmentation models may lead to catastrophic forgetting of previously seen classes.<n>ProtoGuard and PROPEL are proposed to address the problem of catastrophic forgetting.<n>Our approach achieves remarkable results on both the S3DIS and ScanNet datasets.
  arXiv  Detail & Related papers  (2025-04-02T11:58:04Z)
• CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation [67.36817440834251]
  We propose a unified framework for textbfCLass-incremental textbfImbalance-aware textbf3DIS.<n>Our approach achieves state-of-the-art results, surpassing prior work by up to 16.76% mAP for instance segmentation and approximately 30% mIoU for semantic segmentation.
  arXiv  Detail & Related papers  (2025-02-24T18:58:58Z)
• CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection [7.205000222081269]
  Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds. We introduce contrastive semantics mining, which enables the network to extract discriminative categorical features. Through refined primitive geometric structures, the transferability of feature encoding from base to novel classes is significantly enhanced.
  arXiv  Detail & Related papers  (2024-08-30T06:13:49Z)
• Rethinking Few-shot 3D Point Cloud Semantic Segmentation [62.80639841429669]
  This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS) We focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. To address these issues, we introduce a standardized FS-PCS setting, upon which a new benchmark is built.
  arXiv  Detail & Related papers  (2024-03-01T15:14:47Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.