Semantic segmentation in 3D point-clouds plays an essential role in various applications, such as autonomous driving, robot control, and mapping. In general, a segmentation model trained on one source domain suffers a severe decline in performance when applied to a different target domain due to the cross-domain discrepancy. Various Unsupervised Domain Adaptation (UDA) approaches have been proposed to tackle this issue. However, most are only for uni-modal data and do not explore how to learn from the multi-modality data containing 2D images and 3D point clouds. We propose an Adversarial Unsupervised Domain Adaptation (AUDA) based 3D semantic segmentation framework for achieving this goal. The proposed AUDA can leverage the complementary information between 2D images and 3D point clouds by cross-modal learning and adversarial learning. On the other hand, there is a highly imbalanced data distribution in real scenarios. We further develop a simple and effective threshold-moving technique during the final inference stage to mitigate this issue. Finally, we conduct experiments on three unsupervised domain adaptation scenarios, ie., Country-to-Country (USA →Singapore), Day-to-Night, and Dataset-to-Dataset (A2D2 →SemanticKITTI). The experimental results demonstrate the effectiveness of proposed method that can significantly improve segmentation performance for rare classes. Code and trained models are available at https://github.com/weiliu-ai/auda.

3D点云中的语义分割在诸如自动驾驶，机器人控制和地图绘制等各种应用中起着至关重要的作用。通常，由于跨域差异，在一个源域上训练的细分模型在应用于其他目标域时，性能会严重下降。已经提出了各种无监督域自适应（UDA）方法来解决这个问题。但是，大多数仅用于单峰数据，而不探索如何从包含2D图像和3D点云的多峰数据中学习。我们提出了一种基于对抗性无监督域自适应（AUDA）的3D语义分割框架，以实现这一目标。拟议的AUDA可以通过交叉模式学习和对抗学习来利用2D图像和3D点云之间的补充信息。另一方面，在实际方案中数据分布非常不平衡。我们在最终推断阶段进一步开发了一种简单有效的阈值移动技术，以缓解此问题。最后，我们在三种无监督的领域自适应方案中进行了实验，即国家对国家（美国→新加坡），日对夜和数据集到数据集（A2D2→SemanticKITTI）。实验结果证明了所提出方法的有效性，该方法可以显着提高稀有类别的分割性能。代码和经过训练的模型可在https://github.com/weiliu-ai/auda中获得。