Dual Structural Knowledge Interaction for Domain Adaptation
文献类型：期刊论文
| 作者 | Zuo, Yukun1; Yao, Hantao2 ; Zhuang, Liansheng1; Xu, Changsheng2,3
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2023 |
| 卷号 | 25页码:9057-9070 |
| ISSN号 | 1520-9210 |
| 关键词 | Manifolds Feature extraction Adaptation models Representation learning Task analysis Semisupervised learning Pattern recognition Domain adaptation structural knowledge dual structural knowledge interaction |
| DOI | 10.1109/TMM.2023.3245420 |
| 通讯作者 | Xu, Changsheng(csxu@nlpr.ia.ac.cn) |
| 英文摘要 | Domain adaptation aims to transfer knowledge from a label-rich source domain to an unlabeled target domain. A common strategy is to assign pseudo-labels to unlabeled target samples for performing representation learning. However, most existing methods only apply the source-guided classifier to generate the source-biased pseudo-labels for self-training, leading to biased target representations. Moreover, the generated pseudo-labels ignore the manifold assumption that neighboring samples are likely to have the same labels. To address the above problem, we formulate a novel structural knowledge to assign target-oriented and manifold-guided pseudo-labels for unlabeled target samples. The structural knowledge consists of cluster-based knowledge and locality-based knowledge. The cluster-based knowledge denotes the label consistency between the target samples and the non-parametric target cluster centers, making the pseudo-labels target-oriented. The locality-based knowledge constrains the target sample and its neighbors to satisfy the manifold assumption. As the neighbors contain the source and target samples, the source and target locality-based knowledge are utilized to boost the descriptions. With the structural knowledge, we propose a novel Dual Structural Knowledge Interaction (DSKI) framework for domain adaptation. For generating aligned and discriminative features, knowledge consistency constraint and instance mutual constraint are proposed in DSKI. Evaluations on three benchmarks demonstrate the effectiveness of the Dual Structural Knowledge Interaction, e.g., 74.9%, 87.7%, and 90.8% for Office-Home, VisDa-2017, and Office-31, respectively. |
| WOS关键词 | ALIGNMENT |
| 资助项目 | National Key Research and Development Program of China |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:001133324200032 |
| 资助机构 | National Key Research and Development Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/54829]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Xu, Changsheng |
| 作者单位 | 1.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,et al. Dual Structural Knowledge Interaction for Domain Adaptation[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:9057-9070. |
| APA | Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,&Xu, Changsheng.(2023).Dual Structural Knowledge Interaction for Domain Adaptation.IEEE TRANSACTIONS ON MULTIMEDIA,25,9057-9070. |
| MLA | Zuo, Yukun,et al."Dual Structural Knowledge Interaction for Domain Adaptation".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):9057-9070. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。