论文标题
深度辅助残留物，用于跨域空中图像语义分割
Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation
论文作者
论文摘要
无监督的域适应性（UDA）是最大程度地减少域间隙的方法。生成方法是最小化航空图像域间隙的常见方法，可改善下游任务的性能，例如跨域语义分割。对于航空图像，数字表面模型（DSM）通常在源域和目标域中可用。 DSM中的深度信息将外部信息带入生成模型。但是，很少有研究利用它。在本文中，提出了深度辅助残留物（DRDG），其中使用深度监督损失（DSL）和深度周期一致性损失（DCCL）将深度信息带入生成模型。实验结果表明，DRDG在跨域语义分割任务中的生成方法之间达到了最新的精度。
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.
