通过增强与伪标签提升跨平台3D检测泛化能力
Towards Cross-Platform Generalization: Domain Adaptive 3D Detection with Augmentation and Pseudo-Labeling
- 结合点云与体素特征，用自适应增强缩小领域差异
- 在目标域上实现车类62.67%、行人49.81%的检测精度
- 适合需要跨传感器部署的自动驾驶检测系统
本技术报告展示了在RoboSense2025挑战赛中获得奖项的跨平台3D目标检测解决方案。方法基于PVRCNN++框架，有效融合点云与体素特征。在此基础上，通过定制化数据增强和伪标签自训练策略，缩小不同平台间的领域差异，显著提升模型泛化能力。最终在挑战赛中取得第三名，于第一阶段目标域上实现车类3D AP为62.67%，第二阶段目标域上车类与行人分别达到58.76%与49.81%的检测精度。
原文摘要 · Abstract (English)
This technical report represents the award-winning solution to the Cross-platform 3D Object Detection task in the RoboSense2025 Challenge. Our approach is built upon PVRCNN++, an efficient 3D object detection framework that effectively integrates point-based and voxel-based features. On top of this foundation, we improve cross-platform generalization by narrowing domain gaps through tailored data augmentation and a self-training strategy with pseudo-labels. These enhancements enabled our approach to secure the 3rd place in the challenge, achieving a 3D AP of 62.67% for the Car category on the phase-1 target domain, and 58.76% and 49.81% for Car and Pedestrian categories respectively on the phase-2 target domain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。