题名 | Contrastive Bayesian Analysis for Deep Metric Learning |
作者 | |
发表日期 | 2022
|
DOI | |
发表期刊 | |
ISSN | 0162-8828
|
EISSN | 1939-3539
|
卷号 | PP期号:99页码:1-18 |
摘要 | Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabilities of image labels conditioned by their features similarity in a contrastive learning setting. This contrastive Bayesian analysis leads to a new loss function for deep metric learning. To improve the generalization capability of the proposed method onto new classes, we further extend the contrastive Bayesian loss with a metric variance constraint. Our experimental results and ablation studies demonstrate that the proposed contrastive Bayesian metric learning method significantly improves the performance of deep metric learning in both supervised and pseudo-supervised scenarios, outperforming existing methods by a large margin. |
关键词 | |
相关链接 | [Scopus记录] |
收录类别 | |
语种 | 英语
|
学校署名 | 其他
|
EI入藏号 | 20224613123839
|
EI主题词 | Deep learning
; Distance education
; Job analysis
; Personnel training
|
EI分类号 | Ergonomics and Human Factors Engineering:461.4
; Personnel:912.4
|
ESI学科分类 | ENGINEERING
|
Scopus记录号 | 2-s2.0-85141550015
|
来源库 | Scopus
|
全文链接 | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9946419 |
引用统计 |
被引频次[WOS]:14
|
成果类型 | 期刊论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/411908 |
专题 | 南方科技大学 |
作者单位 | 1.School of Computer Science and Engineering, Central South University, Changsha, Hunan, China 2.Guangdong Multimedia Information Service Engineering Technology Research Center, Shenzhen University, China 3.Institute of Information Science, School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China 4.Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA 5.Faculty of Technical Sciences University of Kragujevac, Cacak, Serbia 6.Southern University of Science and Technology, Shenzhen, China |
推荐引用方式 GB/T 7714 |
Kan,Shichao,He,Zhiquan,Cen,Yigang,et al. Contrastive Bayesian Analysis for Deep Metric Learning[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2022,PP(99):1-18.
|
APA |
Kan,Shichao,He,Zhiquan,Cen,Yigang,Li,Yang,Mladenovic,Vladimir,&He,Zhihai.(2022).Contrastive Bayesian Analysis for Deep Metric Learning.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,PP(99),1-18.
|
MLA |
Kan,Shichao,et al."Contrastive Bayesian Analysis for Deep Metric Learning".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE PP.99(2022):1-18.
|
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