Existing point cloud semantic segmentation networks cannot identify unknown classes and update their knowledge, due to a closed-set and static perspective of the real world, which would induce the intelligent agent to make bad decisions. To address this problem, we propose a Probability-Driven Framework (PDF) for open world semantic segmentation that includes (i) a lightweight U-decoder branch to identify unknown classes by estimating the uncertainties, (ii) a flexible pseudo-labeling scheme to supply geometry features along with probability distribution features of unknown classes by generating pseudo labels, and (iii) an incremental knowledge distillation strategy to incorporate novel classes into the existing knowledge base gradually. Our framework enables the model to behave like human beings, which could recognize unknown objects and incrementally learn them with the corresponding knowledge. Experimental results on the S3DIS and ScanNetv2 datasets demonstrate that the proposed PDF outperforms other methods by a large margin in both important tasks of open world semantic segmentation.

翻译：现有的点云语义分割网络由于采用封闭静态的现实世界视角，无法识别未知类别并更新其知识，这将导致智能体做出错误决策。为解决此问题，我们提出一种面向开放世界语义分割的概率驱动框架（PDF），其包含：（i）轻量化U型解码器分支，通过不确定性估计识别未知类别；（ii）灵活伪标注方案，通过生成伪标签提供未知类别的几何特征与概率分布特征；（iii）渐进式知识蒸馏策略，将新类别逐步整合至现有知识库。本框架使模型能够模拟人类行为，即可识别未知物体并利用相应知识进行增量学习。在S3DIS与ScanNetv2数据集上的实验结果表明，所提出的PDF在开放世界语义分割的两项核心任务中均显著优于现有方法。