Knowledge Commons of Institute of Automation,CAS
Adversarial Domain Adaptation with a Domain Similarity Discriminator for Semantic Segmentation of Urban Areas | |
Liang Yan1,2; Bin Fan1,2; Shiming Xiang1,2; Chunhong Pan2 | |
2018-10 | |
会议名称 | IEEE International Conference on Image Processing |
会议录名称 | 2018 25th IEEE International Conference on Image Processing (ICIP) |
会议日期 | 7-10 Oct. 2018 |
会议地点 | Athens, Greece |
摘要 | Existing semantic segmentation models of urban areas have shown to perform well in a supervised setting. However, collecting lots of annotated images from each city to train such models is time-consuming or difficult. In addition, when transferring the segmentation model from the trained city (source domain) to an unseen city (target domain), the performance will largely degrade due to the domain shift. For this reason, we propose a domain adaptation method with a domain similarity discriminator to eliminate such domain shift in the framework of adversarial learning. Contrary to the single-input adversarial network, our domain similarity discriminator, which consists of a Siamese network, is able to measure the similarity of the pairwise-input data. In this way, we can use more information about the pairwise-input to measure the similarity between different distributions so as to address the problem of domain shift. Experimental results demonstrate that our approach outperforms the competing methods on three different cities. |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/ICIP.2018.8451010 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44358 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
作者单位 | 1.School of Artificial Intelligence Institute, University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Liang Yan,Bin Fan,Shiming Xiang,et al. Adversarial Domain Adaptation with a Domain Similarity Discriminator for Semantic Segmentation of Urban Areas[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ADVERSARIAL DOMAIN A(858KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论