Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation

Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting pixels. Such vanilla methods are usually suboptimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. The model suffers from confusion in predicting the target domain due to the unrealistic mixing. For instance, it is not reasonable to directly paste the near "pedestrian" pixels into the remote "sky" area. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix categories and facilitate two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) for data augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to obtain the pseudo depth. Extensive experiments show that our methods, even with pseudo depth, achieve competitive performance, i.e., 77.7 mIoU on GTA→Cityscapes and 69.3 mIoU on Synthia→Cityscapes.