Semantic Segmentation via Domain Adaptation with Global Structure Embedding
2019 IEEE Visual Communications and Image Processing (VCIP)(2019)
摘要
In this paper we focus on the problem of unsupervised domain adaptation for semantic segmentation. The previous works usually focus on adversarial learning either in pixel-level or feature-level. However, global structure knowledge is often neglected in the adversarial learning due to the possible reasons: First, the result of pixel-level adversarial learning does not necessarily preserve the semantic consistency of the input image. Second, global structure knowledge is not embedded to regularize the feature-level adversarial learning. In this work, we propose a framework for unsupervised domain adaptation in semantic segmentation which effectively incorporates pixel- level, feature-level adversarial learning and self-training strategy. Our framework embeds the global structure knowledge into the adversarial training step to tackle the problem of structure misalignment. Consequently, our proposed framework achieves the state-of-the-art semantic segmentation domain adaptation results on the task of transferring GTA5 to Cityscapes.
更多查看译文
关键词
semantic segmentation,domain adaptation
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