基于渐进批次交替训练的3D目标检测领域自适应
Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Training
AI总结：
本文提出渐进批次交替训练策略，通过逐步减少源域数据、增加目标域数据的方式实现LiDAR 3D目标检测的领域自适应，在四个自动驾驶数据集上取得显著性能提升。
摘要：
我们研究基于LiDAR的3D目标检测中的领域自适应问题。为此，我们提出一种简单而有效的训练策略，称为渐进批次交替（Gradual Batch Alternation），能够从大规模有标注的源域适应到标注不足的目标域。其思想是以交替方式使用来自源域和目标域数据的样本批次启动训练，但随着训练进行，逐步减少源域数据的使用量。通过这种方式，模型缓慢地向目标域偏移，并最终更好地适应目标域。在四个基准自动驾驶数据集ONCE、PandaSet、Waymo和nuScenes上进行的3D目标检测领域自适应实验表明，与现有方法和强基线相比，该策略取得了显著的性能提升。
英文摘要：
We consider the problem of domain adaptation in LiDAR-based 3D object detection. Towards this, we propose a simple yet effective training strategy called Gradual Batch Alternation that can adapt from a large labeled source domain to an insufficiently labeled target domain. The idea is to initiate the training with the batch of samples from the source and target domain data in an alternate fashion, but then gradually reduce the amount of the source domain data over time as the training progresses. This way the model slowly shifts towards the target domain and eventually better adapt to it. The domain adaptation experiments for 3D object detection on four benchmark autonomous driving datasets, namely ONCE, PandaSet, Waymo, and nuScenes, demonstrate significant performance gains over prior arts and strong baselines.
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。
