We introduce Multi-Source 3D (MS3D), a new self-training pipeline for unsupervised domain adaptation in 3D object detection. Despite the remarkable accuracy of 3D detectors, they often overfit to specific domain biases, leading to suboptimal performance in various sensor setups and environments. Existing methods typically focus on adapting a single detector to the target domain, overlooking the fact that different detectors possess distinct expertise on different unseen domains. MS3D leverages this by combining different pre-trained detectors from multiple source domains and incorporating temporal information to produce high-quality pseudo-labels for fine-tuning. Our proposed Kernel-Density Estimation (KDE) Box Fusion method fuses box proposals from multiple domains to obtain pseudo-labels that surpass the performance of the best source domain detectors. MS3D exhibits greater robustness to domain shifts and produces accurate pseudo-labels over greater distances, making it well-suited for high-to-low beam domain adaptation and vice versa. Our method achieved state-of-the-art performance on all evaluated datasets, and we demonstrate that the choice of pre-trained source detectors has minimal impact on the self-training result, making MS3D suitable for real-world applications.

翻译：我们提出了多源三维（MS3D）——一种用于三维目标检测无监督域自适应的新型自训练流程。尽管三维检测器具有卓越的准确性，但它们常常过拟合于特定领域的偏差，导致在不同传感器设置和环境中的性能欠佳。现有方法通常侧重于将单一检测器适配到目标域，忽略了不同检测器在面对不同未知域时具有各自独特专长的事实。MS3D通过结合来自多个源域的不同预训练检测器，并融入时间信息以生成高质量伪标签进行微调，从而利用了这一点。我们提出的核密度估计（KDE）框融合方法融合来自多个域的框提议，获得超越最佳源域检测器性能的伪标签。MS3D对域偏移表现出更强的鲁棒性，并能生成更远距离上的精确伪标签，使其特别适用于高线束到低线束域自适应的双向转换。我们的方法在所有评估数据集上均取得了最先进的性能，同时我们证明了预训练源检测器的选择对自训练结果影响极小，这使得MS3D适用于实际应用。