提出分层正交原型框架，解决3D点云少样本分割中新类学习导致旧类遗忘的问题。
Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation
- 通过分层正交化解耦基础与新类的学习过程，降低干扰。
- 在1-shot和5-shot设置下，ScanNet200/++上均优于现有方法。
- 适合需要稳定少样本适应能力的3D点云分割任务。
通用少样本3D点云分割旨在仅用少量标注就适应新类别，同时保持对基础类别的强性能，但受制于稳定性与可塑性之间的权衡：适应新类别可能干扰共享表征，导致基础类别遗忘。本文提出HOP3D，一种统一框架，通过熵驱动的少样本正则化学习分层正交原型，实现对新类别的鲁棒适应而不损害基础类别性能。HOP3D引入分层正交化机制，在梯度与表征层面解耦基础类与新类的学习，有效缓解两者间的干扰。为进一步提升稀疏监督下的适应能力，引入基于熵的正则化项，利用预测不确定性来优化原型学习并促进平衡预测。在ScanNet200与ScanNet++上的大量实验表明，HOP3D在1-shot与5-shot设置下均持续优于当前最优基线。代码已公开于https://fdueblab-hop3d.github.io/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。