Most existing 3D point cloud object detection approaches heavily rely on large amounts of labeled training data. However, the labeling process is costly and time-consuming. This paper considers few-shot 3D point cloud object detection, where only a few annotated samples of novel classes are needed with abundant samples of base classes. To this end, we propose Prototypical VoteNet to recognize and localize novel instances, which incorporates two new modules: Prototypical Vote Module (PVM) and Prototypical Head Module (PHM). Specifically, as the 3D basic geometric structures can be shared among categories, PVM is designed to leverage class-agnostic geometric prototypes, which are learned from base classes, to refine local features of novel categories.Then PHM is proposed to utilize class prototypes to enhance the global feature of each object, facilitating subsequent object localization and classification, which is trained by the episodic training strategy. To evaluate the model in this new setting, we contribute two new benchmark datasets, FS-ScanNet and FS-SUNRGBD. We conduct extensive experiments to demonstrate the effectiveness of Prototypical VoteNet, and our proposed method shows significant and consistent improvements compared to baselines on two benchmark datasets.
翻译:大多数现有的3D点云体探测方法都严重依赖大量贴标签的培训数据。然而,标签过程既费钱又费时。本文考虑了微小的 3D点云体探测方法,其中只需要少数附加说明的新类样本,并有大量基级样本。为此,我们提议采用Protodic VoteNet来识别和定位新案例,其中包括两个新模块:Protomodal投票模块(PVM)和Protomodrodic Head模块(PHM)。具体地说,由于3D基本几何结构可以在各类别之间共享,PVM旨在利用从基级学到的等级-Agnotic几何原型模型,以完善新类的本地特征。然后,PHM建议利用类原型来增强每个对象的全球特征,促进随后的物体定位和分类,该新对象的定位和分类工作由感官培训战略培训。为了评价这一新设置的模型,我们贡献了两个新的基准数据集:FS-ScanNet和FS-SUNRGBD。我们进行了广泛的实验,以展示Prototodal Valeving bas bas的基准比照两个基准。我们提出的方法显示了显著的改进。