Exploring uncertainty in pseudo-label guided unsupervised domain adaptation
文献类型：期刊论文
| 作者 | Liang, Jian1,2,3 ; He, Ran1,3,4; Sun, Zhenan1,3,4; Tan, Tieniu1,3,4
|
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2019-12-01 |
| 卷号 | 96页码:11 |
| 关键词 | Unsupervised domain adaptation Pseudo labeling Feature transformation Progressive learning Transfer learning |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2019.106996 |
| 通讯作者 | Liang, Jian(liangjian92@gmail.com) |
| 英文摘要 | Due to the unavailability of labeled target data, most existing unsupervised domain adaptation (UDA) methods alternately classify the unlabeled target samples and discover a low-dimensional subspace by mitigating the cross-domain distribution discrepancy. During the pseudo-label guided subspace discovery step, however, the posterior probabilities (uncertainties) from the previous target label estimation step are totally ignored, which may promote the error accumulation and degrade the adaptation performance. To address this issue, we propose to progressively increase the number of target training samples and incorporate the uncertainties to accurately characterize both cross-domain distribution discrepancy and other infra-domain relations. Specifically, we exploit maximum mean discrepancy (MMD) and within class variance minimization for these relations, yet, these terms merely focus on the global class structure while ignoring the local structure. Then, a triplet-wise instance-to-center margin is further maximized to push apart target instances and source class centers of different classes and bring closer them of the same class. Generally, an EM-style algorithm is developed by alternating between inferring uncertainties, progressively selecting certain training target samples, and seeking the optimal feature transformation to bridge two domains. Extensive experiments on three popular visual domain adaptation datasets demonstrate that our method significantly outperforms recent state-of-the-art approaches. (C) 2019 Elsevier Ltd. All rights reserved. |
| WOS关键词 | KERNEL |
| 资助项目 | State Key Development Program[2016YFB1001001] ; National Natural Science Foundation of China[61622310] ; National Natural Science Foundation of China[61473289] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000487569700042 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | State Key Development Program ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/26441]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Liang, Jian |
| 作者单位 | 1.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China 2.NUS, Dept ECE, Singapore, Singapore 3.UCAS, Beijing, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liang, Jian,He, Ran,Sun, Zhenan,et al. Exploring uncertainty in pseudo-label guided unsupervised domain adaptation[J]. PATTERN RECOGNITION,2019,96:11. |
| APA | Liang, Jian,He, Ran,Sun, Zhenan,&Tan, Tieniu.(2019).Exploring uncertainty in pseudo-label guided unsupervised domain adaptation.PATTERN RECOGNITION,96,11. |
| MLA | Liang, Jian,et al."Exploring uncertainty in pseudo-label guided unsupervised domain adaptation".PATTERN RECOGNITION 96(2019):11. |
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。