Fuzzy Inference Attention Module for Unsupervised Domain Adaptation
文献类型：期刊论文
| 作者 | Wang, Zhengshan1; Chen, Long1 ; Wang, Fei-Yue2,3,4
|
| 刊名 | IEEE TRANSACTIONS ON FUZZY SYSTEMS
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 32期号:4页码:1706-1718 |
| 关键词 | Attention module domain adaptation (DA) fuzzy inference system (FIS) negative transfer (NL) |
| ISSN号 | 1063-6706 |
| DOI | 10.1109/TFUZZ.2023.3332751 |
| 通讯作者 | Chen, Long(longchen@umac.mo) |
| 英文摘要 | Unsupervised domain adaptation (UDA) aims to transfer knowledge acquired from the labeled source domain to the unlabeled target domain. However, the quality of samples can vary greatly. While partial samples are dominated by high-quality domain-invariant class-related information, others may only contain irrelevant domain-specific information or useless random noise. Treating all samples equally may lead to negative transfer, significantly impairing the performance. To address the issue of varying sample quality, we propose an attention module to emphasize the samples that are most suitable for transfer. Within the attention module, we have designed a fuzzy inference system to assess the quality of data based on its class and domain information. Such a fuzzy inference attention (FIA) module demonstrates strong interpretability due to its consideration of the fuzzy nature inherent in class and domain information within the data. FIA also has high flexibility and extensibility as the rule base can be easily adjusted by expert knowledge. More importantly, FIA does not use any parameters requiring training and has a low overhead. This makes it fast and applicable to most existing UDA methods. The experiments on several benchmark datasets prove that FIA can bring significant improvement to existing methods. |
| 资助项目 | Science and Technology Development Fund, Macao S.A.R |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001196731700067 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Science and Technology Development Fund, Macao S.A.R |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58086]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
| 通讯作者 | Chen, Long |
| 作者单位 | 1.Univ Macau, Fac Sci & Technol, Dept Comp & Informat Sci, Macau 999078, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Qingdao Acad Intelligent Ind, Parallel Blockchain Technol Innovat Ctr, Qingdao 266109, Peoples R China 4.Natl Univ Def Technol, Res Ctr Mil Computat Expt & Parallel Syst, Changsha 410073, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Zhengshan,Chen, Long,Wang, Fei-Yue. Fuzzy Inference Attention Module for Unsupervised Domain Adaptation[J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS,2024,32(4):1706-1718. |
| APA | Wang, Zhengshan,Chen, Long,&Wang, Fei-Yue.(2024).Fuzzy Inference Attention Module for Unsupervised Domain Adaptation.IEEE TRANSACTIONS ON FUZZY SYSTEMS,32(4),1706-1718. |
| MLA | Wang, Zhengshan,et al."Fuzzy Inference Attention Module for Unsupervised Domain Adaptation".IEEE TRANSACTIONS ON FUZZY SYSTEMS 32.4(2024):1706-1718. |
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。