arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04744cs.CVcs.AI
收藏

大规模点云的弱监督语义分割

Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud

Xiamen University(厦门大学);East China Normal University(华东师范大学);JD AI Research(京东人工智能研究院)

Yachao Zhang, Zonghao Li, Yuan Xie, Yanyun Qu, Cuihua Li, Tao Mei

摘要:

现有的大规模点云语义分割方法需要昂贵、繁琐且容易出错的手动逐点注释。直观的弱监督训练是降低标签成本的直接解决方案。然而,对于弱监督的大规模点云语义分割,标注过少必然导致网络学习效果不佳。我们提出了一个有效的弱监督方法包含两个组件来解决上述问题。首先,我们构建一个借口任务,\textit{i.e.,}点云着色,与自监督学习转移学习的先验知识,从大量的未标记的点云到一个弱监督网络。通过这种方式,弱监督网络的表示能力可以通过异构任务的指导来提高。此外,为了给未标记数据生成伪标签,提出了一种稀疏标签传播机制,利用生成的类原型来度量未标记点的分类置信度。我们的方法进行了评估大规模点云数据集与不同的场景,包括室内和室外。实验结果表明,大的增益对现有的弱监督和可比的结果完全监督的方法\footnote{Code based on mindspore: https://github.com/dmcv-ecnu/MindSpore\_ModelZoo/tree/main/WS3\_MindSpore}。

英文摘要:

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost of labeling. However, for weakly supervised large-scale point cloud semantic segmentation, too few annotations will inevitably lead to ineffective learning of network. We propose an effective weakly supervised method containing two components to solve the above problem. Firstly, we construct a pretext task, \textit{i.e.,} point cloud colorization, with a self-supervised learning to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network. In this way, the representation capability of the weakly supervised network can be improved by the guidance from a heterogeneous task. Besides, to generate pseudo label for unlabeled data, a sparse label propagation mechanism is proposed with the help of generated class prototypes, which is used to measure the classification confidence of unlabeled point. Our method is evaluated on large-scale point cloud datasets with different scenarios including indoor and outdoor. The experimental results show the large gain against existing weakly supervised and comparable results to fully supervised methods\footnote{Code based on mindspore: https://github.com/dmcv-ecnu/MindSpore\_ModelZoo/tree/main/WS3\_MindSpore}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑