论文标题
几个射击3D点云对象检测的原型votenet检测
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
论文作者
论文摘要
大多数现有的3D点云对象检测方法在很大程度上依赖大量标记的训练数据。但是，标签过程是昂贵且耗时的。本文考虑了很少的3D点云对象检测，其中只需要提供大量基本类别的新颖类的带注释的样本。为此，我们提出了典型的投票网，以识别和本地化新颖实例，其中包含了两个新模块：典型投票模块（PVM）和典型的头部模块（PHM）。具体而言，由于可以在类别之间共享3D基本的几何结构，因此PVM旨在利用类别无形的几何原型（从基础类别中学到的阶级无形的几何原型）来完善新型类别的本地特征。然后建议使用类原型来提高每个对象的全球特征，以促进策略和培训。为了在这种新环境中评估该模型，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证明原型投票机的有效性，与两个基准数据集中的基准相比，我们提出的方法显示出显着且一致的改进。
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.
