Knowledge Commons of Institute of Automation,CAS
AdaptiveFace: Adaptive Margin and Sampling for Face Recognition | |
Hao Liu; Xiangyu Zhu; Zhen Lei; Stan Z.Li | |
2019 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
会议日期 | 2019/6/16-2019/6/20 |
会议地点 | Long Beach, USA |
摘要 | Training large-scale unbalanced data is the central topic in face recognition. In the past two years, face recognition has achieved remarkable improvements due to the introduction of margin based Softmax loss. However, these methods have an implicit assumption that all the classes possess sufficient samples to describe its distribution, so that a manually set margin is enough to equally squeeze each intra-class variations. However, real face datasets are highly unbalanced, which means the classes have tremendously different numbers of samples. In this paper, we argue that the margin should be adapted to different classes. We propose the Adaptive Margin Softmax to adjust the margins for different classes adaptively. In addition to the unbalance challenge, face data always consists of large-scale classes and samples. Smartly selecting valuable classes and samples to participate in the training makes the training more effective and efficient. To this end, we also make the sampling process adaptive in two folds: Firstly, we propose the Hard Prototype Mining to adaptively select a small number of hard classes to participate in classification. Secondly, for data sampling, we introduce the Adaptive Data Sampling to find valuable samples for training adaptively. We combine these three parts together as AdaptiveFace. Extensive analysis and experiments on LFW, LFW BLUFR and MegaFace show that our method performs better than state-of-the-art methods using the same network architecture and training dataset. Code is available at https://github.com/haoliu1994/AdaptiveFace. |
七大方向——子方向分类 | 生物特征识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/25822 |
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 | Zhen Lei |
作者单位 | 模式识别国家重点实验室 |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Hao Liu,Xiangyu Zhu,Zhen Lei,et al. AdaptiveFace: Adaptive Margin and Sampling for Face Recognition[C],2019. |
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 | ||
Adaptiveface Adaptiv(666KB) | 会议论文 | 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