CASIA OpenIR  > 模式识别国家重点实验室  > 生物识别与安全技术
Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition
Guo JZ(郭建珠)1,2; Zhu XY(朱翔昱)1,2; Lei Z(雷震)1,2,3; Li ZQ(李子青)4
Source PublicationIEEE Transactions on Information Forensics and Security
ISSN1556-6013
2021-04
Volume16Issue:-Pages:3082-3095
Subtype人脸识别
Abstract

Face recognition systems are sometimes deployed to a target domain with limited unlabeled samples available. For instance, a model trained on the large-scale webfaces may be required to adapt to a NIR-VIS scenario via very limited unlabeled faces. This situation poses a great challenge to Unsupervised Domain Adaptation with Limited samples for Face Recognition (UDAL-FR), which is less studied in previous works. In this paper, with deep learning methods, we propose a novel training remedy by decomposing the model into the weight parameters and the BN statistics in the training phase. Based on decomposing, we design a novel framework via meta-learning, called Decomposed Meta Batch Normalization (DMBN) for fast domain adaptation in face recognition. DMBN trains the network such that domain-invariant information is prone to store in the weight parameters and domain-specific knowledge tends to be represented by the BN statistics. Specifically, DMBN constructs distribution-shifted tasks via domain-aware sampling, on which several meta-gradients are obtained by optimizing discriminative representations across different BNs. Finally, the weight parameters are updated with these meta-gradients for better consistency across different BNs. With the learned weight parameters, the adaptation is very fast since only the BN updating on limited data is needed. We propose two UDAL-FR benchmarks to evaluate the domain-adaptive ability of a model with limited unlabeled samples. Extensive experiments validate the efficacy of our proposed DMBN.

KeywordFace recognition unsupervised domain adaptation meta-learning batch normalization
MOST Discipline Catalogue工科-计算机科学
DOI10.1109/TIFS.2021.3073823
Indexed BySCI
Language英语
Sub direction classification生物特征识别
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/44371
Collection模式识别国家重点实验室_生物识别与安全技术
Corresponding AuthorLei Z(雷震)
Affiliation1.中国科学院自动化所
2.西湖大学
3.中国科学院大学
4.中国科学院香港创新研究院
Recommended Citation
GB/T 7714
Guo JZ,Zhu XY,Lei Z,et al. Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition[J]. IEEE Transactions on Information Forensics and Security,2021,16(-):3082-3095.
APA Guo JZ,Zhu XY,Lei Z,&Li ZQ.(2021).Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition.IEEE Transactions on Information Forensics and Security,16(-),3082-3095.
MLA Guo JZ,et al."Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition".IEEE Transactions on Information Forensics and Security 16.-(2021):3082-3095.
Files in This Item: Download All
File Name/Size DocType Version Access License
[TIFS2021][Decompose(4808KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Guo JZ(郭建珠)]'s Articles
[Zhu XY(朱翔昱)]'s Articles
[Lei Z(雷震)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Guo JZ(郭建珠)]'s Articles
[Zhu XY(朱翔昱)]'s Articles
[Lei Z(雷震)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Guo JZ(郭建珠)]'s Articles
[Zhu XY(朱翔昱)]'s Articles
[Lei Z(雷震)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: [TIFS2021][Decomposed Meta Batch Normalization for Fast Domain Adaptation in Face Recognition].pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.