论文标题
提案折磨：基于激光雷达的3D对象检测的无监督预训练
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection
论文作者
论文摘要
现有的无监督点云预训练的方法被限制在场景级别或点/体素级实例歧视上。场景级别的方法往往会失去对识别道路对象至关重要的本地细节，而点/体素级方法固有地遭受了有限的接收领域，而这种接收领域无法感知大型对象或上下文环境。考虑到区域级表示形式更适合3D对象检测，我们设计了一个新的无监督点云预训练框架，称为提案contrast，该框架通过对比的区域建议来学习强大的3D表示。具体而言，通过从每个点云中采样的一组详尽的区域建议，每个建议中的几何点关系是建模用于创建表达性建议表示形式的。为了更好地适应3D检测属性，提案contrast既优化了群体间和柱子间分离，即，在语义类别和对象实例上提高了建议表示的歧视性。在各种3D检测器（即PV-RCNN，Centerpoint，Pointpillars和Pointrcnn）和数据集（即Kitti，Waymo和一次）上验证了提案cont抗对流的概括性和可传递性。
Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road objects, while point/voxel-level methods inherently suffer from limited receptive field that is incapable of perceiving large objects or context environments. Considering region-level representations are more suitable for 3D object detection, we devise a new unsupervised point cloud pre-training framework, called ProposalContrast, that learns robust 3D representations by contrasting region proposals. Specifically, with an exhaustive set of region proposals sampled from each point cloud, geometric point relations within each proposal are modeled for creating expressive proposal representations. To better accommodate 3D detection properties, ProposalContrast optimizes with both inter-cluster and inter-proposal separation, i.e., sharpening the discriminativeness of proposal representations across semantic classes and object instances. The generalizability and transferability of ProposalContrast are verified on various 3D detectors (i.e., PV-RCNN, CenterPoint, PointPillars and PointRCNN) and datasets (i.e., KITTI, Waymo and ONCE).
