Knowledge Commons of Institute of Automation,CAS
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 | |
发表期刊 | IEEE Transactions on Information Forensics and Security |
ISSN | 1556-6013 |
2021-04 | |
卷号 | 16期号:-页码:3082-3095 |
文章类型 | 人脸识别 |
摘要 | 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. |
关键词 | Face recognition unsupervised domain adaptation meta-learning batch normalization |
学科门类 | 工科-计算机科学 |
DOI | 10.1109/TIFS.2021.3073823 |
收录类别 | SCI |
语种 | 英语 |
七大方向——子方向分类 | 生物特征识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44371 |
专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
通讯作者 | Lei Z(雷震) |
作者单位 | 1.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 |
推荐引用方式 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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
[TIFS2021][Decompose(4808KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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