Siyuan Yang, Yuan Tang, Min Chen, Jinfeng Xu, Xianzhi Li, Long Hu, Yixue Hao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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) 1 for open world semantic segmentation that includes (i) a lightweight Udecoder 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.00979")
get_code_for_paper("2404.00979")
have("2404.00979")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2404.00979.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2404.00979)
Connect an agent — have() is free.