PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation
This work addresses the challenge of enabling intelligent agents to recognize and learn unknown objects in dynamic environments, which is incremental as it builds on existing segmentation methods with new components for open-world adaptation.
The paper tackles the problem of open world 3D point cloud semantic segmentation, where existing methods fail to identify unknown classes and update knowledge, by proposing a Probability-Driven Framework (PDF) that includes uncertainty estimation, pseudo-labeling, and incremental knowledge distillation, achieving superior performance on S3DIS and ScanNetv2 datasets.
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.