题名 | Adaptive Exploration for Unsupervised Person Re-identification |
作者 | |
发表日期 | 2020-03-01
|
DOI | |
发表期刊 | |
ISSN | 1551-6857
|
EISSN | 1551-6865
|
卷号 | 16期号:1 |
摘要 | Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this article, we propose an Adaptive Exploration (AE) method to address the domain-shift problem for re-ID in an unsupervised manner. Specifically, in the target domain, the re-ID model is inducted to (1) maximize distances between all person images and (2) minimize distances between similar person images. In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move far away from each other. In the second case, according to a similarity threshold, our method adaptively selects neighborhoods for each person image in the feature space. By treating these similar person images as the same class, the non-parametric classifier forces them to stay closer. However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods. As a result, a minority of images may select a large number of neighborhoods while a majority of images has only a few neighborhoods. To address this issue, we additionally integrate a balance strategy into the adaptive selection. We evaluate our methods with two protocols. The first one is called "target-only re-ID", in which only the unlabeled target data is used for training. The second one is called "domain adaptive re-ID", in which both the source data and the target data are used during training. Experimental results on large-scale re-ID datasets demonstrate the effectiveness of our method. Our code has been released at https://github.com/dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification. |
关键词 | |
相关链接 | [Scopus记录] |
收录类别 | |
语种 | 英语
|
学校署名 | 第一
|
WOS研究方向 | Computer Science
|
WOS类目 | Computer Science, Information Systems
; Computer Science, Software Engineering
; Computer Science, Theory & Methods
|
WOS记录号 | WOS:000583712100002
|
出版者 | |
EI入藏号 | 20201608420861
|
EI主题词 | Large dataset
|
EI分类号 | Ergonomics and Human Factors Engineering:461.4
; Data Processing and Image Processing:723.2
|
Scopus记录号 | 2-s2.0-85083085688
|
来源库 | Scopus
|
引用统计 |
被引频次[WOS]:108
|
成果类型 | 期刊论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/138256 |
专题 | 南方科技大学 工学院_环境科学与工程学院_南科大工程技术创新中心(北京) |
作者单位 | 1.SUSTech-UTS Joint Centre of CIS,Southern University of Science and Technology,China 2.Centre for Artificial Intelligence,University of Technology Sydney,Ultimo,Sydney,Australia 3.School of Information Engineering,Zhengzhou University,Zhengzhou, Henan,China |
第一作者单位 | 南方科技大学 |
第一作者的第一单位 | 南方科技大学 |
推荐引用方式 GB/T 7714 |
Ding,Yuhang,Fan,Hehe,Xu,Mingliang,et al. Adaptive Exploration for Unsupervised Person Re-identification[J]. ACM Transactions on Multimedia Computing Communications and Applications,2020,16(1).
|
APA |
Ding,Yuhang,Fan,Hehe,Xu,Mingliang,&Yang,Yi.(2020).Adaptive Exploration for Unsupervised Person Re-identification.ACM Transactions on Multimedia Computing Communications and Applications,16(1).
|
MLA |
Ding,Yuhang,et al."Adaptive Exploration for Unsupervised Person Re-identification".ACM Transactions on Multimedia Computing Communications and Applications 16.1(2020).
|
条目包含的文件 | 条目无相关文件。 |
|
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