利用背景信息增强3D点云少样本增量分割，缓解遗忘问题。
SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
- 从背景区域提取高置信度伪实例，构建原型池以支持新类别学习。
- 在ScanNet和S3DIS上提升新类别IoU达6.98%和3.61%，平均IoU提高1.70%。
- 无需重训练主干网络，适配各类原型方法，适合持续学习场景。
增量少样本（IFS）分割旨在从少量标注中随时间学习新类别。尽管2D领域研究广泛，3D点云上的研究仍不足。现有方法常因灾难性遗忘或稀疏监督下难以学习判别原型而表现不佳，且忽视关键线索：新类别常以未标记背景形式出现在基础训练场景中。本文提出SCOPE（场景上下文原型增强），一种即插即用的背景引导原型增强框架，可集成于任意基于原型的3D分割方法。基础训练后，类无关分割模型从背景区域提取高置信度伪实例，构建原型池。当新类别以少量标注出现时，相关背景原型被检索并融合至少样本原型，生成增强表示，无需重训练主干或增加参数。在ScanNet和S3DIS上的实验表明，SCOPE达到当前最优性能，新类别IoU分别提升6.98%和3.61%，平均IoU提升2.25%和1.70%，同时保持低遗忘率。代码已公开于https://github.com/Surrey-UP-Lab/SCOPE。
原文摘要 · Abstract (English)
Incremental Few-Shot (IFS) segmentation aims to learn new categories over time from only a few annotations. Although widely studied in 2D, it remains underexplored for 3D point clouds. Existing methods suffer from catastrophic forgetting or fail to learn discriminative prototypes under sparse supervision, and often overlook a key cue: novel categories frequently appear as unlabelled background in base-training scenes. We introduce SCOPE (Scene-COntextualised Prototype Enrichment), a plug-and-play background-guided prototype enrichment framework that integrates with any prototype-based 3D segmentation method. After base training, a class-agnostic segmentation model extracts high-confidence pseudo-instances from background regions to build a prototype pool. When novel classes arrive with few labelled samples, relevant background prototypes are retrieved and fused with few-shot prototypes to form enriched representations without retraining the backbone or adding parameters. Experiments on ScanNet and S3DIS show that SCOPE 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, while maintaining low forgetting. Code is available https://github.com/Surrey-UP-Lab/SCOPE.
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。