论文标题
通过逐步批处理培训进行3D对象检测中的域适应
Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Training
论文作者
论文摘要
我们考虑基于LIDAR的3D对象检测中的域适应问题。在此方面，我们提出了一种简单而有效的训练策略，称为渐进的批处理交替，该策略可以从大型标记的源域调整到标记不足的目标域。这个想法是通过替代方式从源和目标域数据的样本中启动培训，但随着时间的推移，随着时间的推移，源域数据的量逐渐减少。这样，模型会慢慢转向目标域，并最终更好地适应它。在四个基准自动驾驶数据集上进行3D对象检测的域适应实验，即一次，Pandaset，Waymo和Nuscenes，在先前的艺术和强质基础上表现出显着的性能提高。
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.
