Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets

arxiv(2023)

引用 0|浏览33
暂无评分
摘要
Point cloud segmentation is a fundamental task in 3D vision that serves a wide range of applications. Although great progresses have been made these years, its practical usability is still limited by the availability of training data. Existing approaches cannot make full use of multiple datasets on hand due to the label mismatch among different datasets. In this paper, we propose a principled approach that supports learning from heterogeneous datasets with different label sets. Our idea is to utilize a pre-trained language model to embed discrete labels to a continuous latent space with the help of their label names. This unifies all labels of different datasets, so that joint training is doable. Meanwhile, classifying points in the continuous 3D space by their vocabulary tokens significantly increase the generalization ability of the model in comparison with existing approaches that have fixed decoder architecture. Besides, we also integrate prompt learning in our framework to alleviate data shifts among different data sources. Extensive experiments demonstrate that our model outperforms the state-of-the-art by a large margin.
更多
查看译文
关键词
unifying point cloud segmentation,datasets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要