arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.01784cs.CV
收藏

COARSE3D:弱监督三维点云分割中的对比学习类原型

COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation

South China University of Technology(华南理工大学);Inria(法国国家信息与自动化研究所)

Rong Li, Anh-Quan Cao, Raoul de Charette

摘要:

大规模3D数据的注释是出了名的麻烦和昂贵。作为替代方案,弱监督学习通过将注释减少几个数量级来满足这种需要。我们提出了COARSE 3D,一种新的架构不可知的对比学习战略的3D分割。由于对比学习需要丰富多样的例子作为键和锚,我们利用一个原型存储体有效地捕获类全局数据集信息到少量的原型作为键。然后,熵驱动的采样技术允许我们从预测中选择好的像素作为锚点。在三个基于投影的主干上的实验表明,我们在三个具有挑战性的真实户外数据集上的表现优于基线,使用低至0.001%的注释。

英文摘要:

Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several order of magnitudes. We propose COARSE3D, a novel architecture-agnostic contrastive learning strategy for 3D segmentation. Since contrastive learning requires rich and diverse examples as keys and anchors, we leverage a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys. An entropy-driven sampling technique then allows us to select good pixels from predictions as anchors. Experiments on three projection-based backbones show we outperform baselines on three challenging real-world outdoor datasets, working with as low as 0.001% annotations.

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。

↑