论文标题
单帧的多帧：3D对象检测的知识蒸馏
Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection
论文作者
论文摘要
3D对象检测的一个常见困境是自主驾驶的，是高质量的，密集的点云仅在训练过程中可用，但不能进行测试。我们使用知识蒸馏来弥合训练时间在高质量输入的模型与推理时间低质量输入测试的模型之间的差距。特别是，我们为点云对象检测设计了两阶段的训练管道。首先，我们在致密点云上训练对象检测模型，该模型仅在训练时使用额外的信息从多个帧生成。然后，我们在稀疏的单帧点云上训练模型的相同对应物，并在两个模型的功能上进行一致性正则化。我们表明，此过程在测试过程中提高了低质量数据的性能，而无需其他开销。
A common dilemma in 3D object detection for autonomous driving is that high-quality, dense point clouds are only available during training, but not testing. We use knowledge distillation to bridge the gap between a model trained on high-quality inputs at training time and another tested on low-quality inputs at inference time. In particular, we design a two-stage training pipeline for point cloud object detection. First, we train an object detection model on dense point clouds, which are generated from multiple frames using extra information only available at training time. Then, we train the model's identical counterpart on sparse single-frame point clouds with consistency regularization on features from both models. We show that this procedure improves performance on low-quality data during testing, without additional overhead.
