Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation

Yao Zhao, Ping Guo, Gaorong Han,Xiuwan Chen

arXiv (Cornell University)(2022)

引用 0|浏览0
暂无评分
摘要
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.
更多
查看译文
关键词
segmentation,depth-assisted,cross-domain
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要