Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation
This work addresses domain gaps in aerial imagery segmentation, which is incremental as it builds on existing generative approaches by adding depth supervision.
The paper tackled the problem of unsupervised domain adaptation for aerial image semantic segmentation by incorporating depth information from digital surface models into a generative model, achieving state-of-the-art accuracy among generative methods.
Unsupervised domain adaptation (UDA) is an approach to minimizing domain gap. Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e.g., cross-domain semantic segmentation. For aerial images, the digital surface model (DSM) is usually available in both the source domain and the target domain. Depth information in DSM brings external information to generative models. However, little research utilizes it. In this paper, depth-assisted ResiDualGAN (DRDG) is proposed where depth supervised loss (DSL), and depth cycle consistency loss (DCCL) are used to bring depth information into the generative model. Experimental results show that DRDG reaches state-of-the-art accuracy between generative methods in cross-domain semantic segmentation tasks.