Gcan: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation | |
Ma, Xinhong2,3,4; Zhang, Tianzhu1,2,4; Xu, Changsheng2,3,4 | |
2019-06 | |
会议日期 | 15-20 June 2019 |
会议地点 | Long Beach, CA, USA |
DOI | 10.1109/CVPR.2019.00846 |
页码 | 8266-8276 |
国家 | USA |
英文摘要 | To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label. Most existing domain adaptation approaches exploit only one or two types of this information and cannot make them complement and enhance each other. Different from existing methods, we propose an end-to-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain label, and class label in a unified deep framework. The proposed GCAN model enjoys several merits. First, to the best of our knowledge, this is the first work to model the three kinds of information jointly in a deep model for unsupervised domain adaptation. Second, the proposed model has designed three effective alignment mechanisms including structure-aware alignment, domain alignment, and class centroid alignment, which can learn domain-invariant and semantic representations effectively to reduce the domain discrepancy for domain adaptation. Extensive experimental results on five standard benchmarks demonstrate that the proposed GCAN algorithm performs favorably against state-of-the-art unsupervised domain adaptation methods. |
会议录 | 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
![]() |
会议录出版者 | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48541] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
通讯作者 | Xu, Changsheng |
作者单位 | 1.University of Science and Technology of China 2.University of Chinese Academy of Sciences (UCAS) 3.Peng Cheng Laboratory, Shenzhen, China 4.National Lab of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) |
推荐引用方式 GB/T 7714 | Ma, Xinhong,Zhang, Tianzhu,Xu, Changsheng. Gcan: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation[C]. 见:. Long Beach, CA, USA. 15-20 June 2019. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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