Open set domain adaptation with latent structure discovery and kernelized classifier learning | |
Tang, Yongqiang2; Tian, Lei1,2; Zhang, Wensheng1,2 | |
刊名 | NEUROCOMPUTING |
2023-04-28 | |
卷号 | 531页码:125-139 |
关键词 | Open set domain adaptation Adaptive graph learning Latent structure discovery Kernelized classifier learning |
ISSN号 | 0925-2312 |
DOI | 10.1016/j.neucom.2023.02.030 |
通讯作者 | Tang, Yongqiang(yongqiang.tang@ia.ac.cn) ; Tian, Lei(tianlei2017@ia.ac.cn) |
英文摘要 | Numerous visual domain adaptation methods have been proposed for transferring knowledge from a well-labeled source domain to an unlabeled but related target domain. Most of existing works are only geared to closed set domain adaptation, where an identical label space is shared between two domains. In this paper, we focus on a more realistic but challenging scenario, open set domain adaptation, where the target domain contains unknown classes that do not appear in the label space of source domain. The main task of open set domain adaptation is to simultaneously recognize the target images of known classes and those of unknown classes correctly. To achieve this goal, in this paper, we propose a novel open set domain adaptation method, which consists of two parts: latent structure discovery and kernel-ized classifier learning. In the first part, we employ an adaptive discriminative graph learning strategy to capture the intrinsic manifold structure of the source and target domain data in the latent feature space, such that the boundaries among all classes will be delineated more clearly. In the second part, the sam -ples from the latent feature space are mapped into a high-dimensional kernel space to make them lin-early separable, and a linear classifier is learned by jointly operating unknown target samples separating, known samples matching and local structure preserving. As the optimization problem is not convex with all variables, we devise an efficient iterative algorithm to solve it. The extensive exper-imental results on five image datasets confirm the superiority of the proposed method compared with the state-of-the-art traditional and deep competitors. (c) 2023 Elsevier B.V. All rights reserved. |
资助项目 | National Key Research and Development Program of China[2018AAA0102000] ; Key -Area Research and Development Program of Guangdong Province[2019B010153002] ; National Natural Science Foundation of China[62106266] ; National Natural Science Foundation of China[U22B2048] ; National Natural Science Foundation of China[62006139] |
WOS关键词 | REGULARIZATION ; PRESERVATION ; FRAMEWORK |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000991720600001 |
资助机构 | National Key Research and Development Program of China ; Key -Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/53405] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Tang, Yongqiang; Tian, Lei |
作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Tang, Yongqiang,Tian, Lei,Zhang, Wensheng. Open set domain adaptation with latent structure discovery and kernelized classifier learning[J]. NEUROCOMPUTING,2023,531:125-139. |
APA | Tang, Yongqiang,Tian, Lei,&Zhang, Wensheng.(2023).Open set domain adaptation with latent structure discovery and kernelized classifier learning.NEUROCOMPUTING,531,125-139. |
MLA | Tang, Yongqiang,et al."Open set domain adaptation with latent structure discovery and kernelized classifier learning".NEUROCOMPUTING 531(2023):125-139. |
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