Domain Adaptation through Photorealistic Enhanced Images for Semantic Segmentation
Domain Adaptation through Photorealistic Enhanced Images for Semantic Segmentation
复制标题
DOI：
10.1155/2022/1848857
复制
发表时间：
2022-07
影响因子：
--
通讯作者：
Takafumi Katayama;Tian Song;Xiantao Jiang;Jenq-Shiou Leu;T. Shimamoto
中科院分区：
文献类型：
--
作者：
Takafumi Katayama;Tian Song;Xiantao Jiang;Jenq-Shiou Leu;T. Shimamoto
在本文中，三种类型的领域自适应，这是定义为图像级域自适应，域间自适应，域内自适应有效地结合起来，构建一个高效的框架，语义分割。所提出的领域自适应平台可以实现在真实的世界中使用真实感图像生成耗尽的监督数据的时间消耗的高度减少。所提出的框架实现了45.0%的平均交集（mIoU）。此外，通过将所提出的方法与域内自适应相结合，与以前的工作相比，实现了1.2%的mIoU的改善。
In this paper, three types of domain adaptation which are defined as image-level domain adaptation, interdomain adaptation, and intradomain adaptation are efficiently combined to construct a high efficiency framework for semantic segmentation. The proposed domain adaptation platform can achieve a high reduction of time-consuming to generate exhausted supervised data in the real world using photorealistic images. The proposed framework achieved a mean Intersection-over-Union (mIoU) of 45.0%. Furthermore, by combining the proposed method with intradomain adaptation, the improvement of 1.2% mIoU is achieved compared to previous work.