Knowledge Commons of Institute of Automation,CAS
GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation | |
Ma, Xinhong1,2,3; Zhang, Tianzhu1,2,4; Xu, Changsheng1,2,3 | |
2019-06 | |
会议名称 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
会议录名称 | IEEE Conference on Computer Vision and Pattern Recognition |
页码 | 8266-8276 |
会议日期 | JUN 16-20, 2019 |
会议地点 | Long Beach, CA, USA |
会议举办国 | USA |
出版者 | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
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. |
DOI | 10.1109/CVPR.2019.00846 |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[U1705262] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; National Natural Science Foundation of China[61721004] ; National Nature Science Foundation of China[61532009] ; Beijing Natural Science Foundation[4172062] ; National Natural Science Foundation of China[61728210] ; National Natural Science Foundation of China[61751211] ; Youth Innovation Promotion Association Chinese Academy of Sciences[2018166] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[U1705262] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; National Natural Science Foundation of China[61721004] ; National Nature Science Foundation of China[61532009] ; Beijing Natural Science Foundation[4172062] ; National Natural Science Foundation of China[61728210] ; National Natural Science Foundation of China[61751211] ; Youth Innovation Promotion Association Chinese Academy of Sciences[2018166] |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods |
WOS记录号 | WOS:000542649301089 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48541 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
通讯作者 | Xu, Changsheng |
作者单位 | 1.National Lab of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) 2.University of Chinese Academy of Sciences (UCAS) 3.Peng Cheng Laboratory, Shenzhen, China 4.University of Science and Technology of China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
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]:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2019:8266-8276. |
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 | ||
Ma_GCAN_Graph_Convol(7239KB) | 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