Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic segmentation models. It consists of a self-training stage, which provides two domain-adapted models, and a model collaboration loop for the mutual improvement of these two models. These models are then used to provide the final semantic segmentation labels (pseudo-labels) for the real-world images. The overall procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for on-board semantic segmentation. Our procedure shows improvements ranging from ~13 to ~26 mIoU points over baselines, so establishing new state-of-the-art results.

翻译：语义图像分割是自动驾驶领域一项核心且具挑战性的任务，通常通过训练深度学习模型来实现。由于此类训练依赖于人工图像标注这一瓶颈，利用自动生成标签的合成图像结合未标注的真实世界图像成为一种有前景的替代方案。这需要解决无监督域适应（UDA）问题。本文针对语义分割模型从合成域到真实域的UDA任务，提出了一种新的联合训练流程。该流程包含一个自训练阶段（可生成两个域适应模型）以及一个用于这两个模型相互改进的模型协同循环。随后利用这些模型为真实世界图像提供最终的语义分割标签（伪标签）。整体流程将深度模型视为黑箱，并在伪标签目标图像层面驱动其协同，既无需修改损失函数，也无需显式特征对齐。我们在标准车载语义分割合成与真实数据集上验证了该方法。与基线相比，本方法实现了约13至26个mIoU点的提升，从而创下新的最优结果。