Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large performance discrepancies due for instance to different lidar patterns or changes in acquisition conditions. This paper addresses the corresponding Unsupervised Domain Adaptation (UDA) task for semantic segmentation. To mitigate this problem, we introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data. As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data. This novel strategy differs from classical minimization of statistical divergences or lidar-specific state-of-the-art domain adaptation techniques. Our experiments demonstrate that our method achieves a better performance than the current state of the art in synthetic-to-real and real-to-real scenarios.

翻译：在标注数据集上训练的模型难以推广至另一领域，因为数据域间可能存在多种偏移。这一问题在激光雷达数据中尤为显著，不同激光雷达扫描模式或采集条件变化等因素可能导致模型性能出现巨大差异。本文针对语义分割任务中的无监督域自适应（UDA）问题展开研究。为缓解该问题，我们提出一项无监督辅助任务，即在源域和目标域数据上同时学习隐式底层曲面表征。由于两个域共享相同的隐式表征，模型被迫适应两数据源之间的差异。这一新颖策略不同于经典的统计散度最小化方法或激光雷达专用领域自适应技术。实验表明，在合成到真实及真实到真实场景下，我们的方法均取得了优于当前最先进技术的性能。