PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation

arXiv:2404.00979v1 Announce Type: new
Abstract: 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 …

abstract agent arxiv cloud cs.cv decisions framework identify intelligent knowledge networks pdf perspective probability segmentation semantic set type update world