一亿ID的人脸识别训练和万亿人脸对(Trillion Pairs)的人脸识别评测

CSDN学习
CSDN学习官方账号
博客专家认证
2018-06-02 02:23:03
海量数据下的分布式训练探索、极端条件下人脸识别的测试、工业界一线的实战经验。可以对深度学习有更好的理解,对训练的细节有更好的把握,对人脸识别有更好的认识,能够培养实战型的分布式训练思维。



 



添加小助手,备注:公开课,邀你加入课程交流群




一亿ID的人脸识别训练和万亿人脸对(Tr
毕业于浙江大学,现为格灵深瞳首席科学家和算法部负责人
本课程会首先带大家一起回顾下人脸识别的概念、历史发展和学术界的最新进展。然后会跟大家聊一下工业界对人脸识别的需求,并分享一些工业界进行大规模人脸识别的经验。最后还会宣布一个比赛,在这个比赛中,我们不仅提供了标注更准确的大规模人脸训练数据集, 而且也提供了一个非常有挑战性且可以支持超低误识别率(1e-12)的线上评测。

相关链接:https://edu.csdn.net/huiyiCourse/detail/791?utm_source=edu_bbs_autocreate
...全文
177 回复 打赏 收藏 转发到动态 举报
写回复
用AI写文章
回复
切换为时间正序
请发表友善的回复…
发表回复
One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large- scale face recognition is the design of appropriate loss func- tions that enhance discriminative power. Centre loss pe- nalises the distance between the deep features and their cor- responding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the lin- ear transformation matrix in the last fully connected layer can be used as a representation of the class centres in an angular space and penalises the angles between the deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to max- imise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to the ex- act correspondence to the geodesic distance on the hyper- sphere. We present arguably the most extensive experimen- tal evaluation of all the recent state-of-the-art face recog- nition methods on over 10 face recognition benchmarks in- cluding a new large-scale image database with trillion level of pairs and a large-scale video dataset. We show that Ar- cFace consistently outperforms the state-of-the-art and can be easily implemented with negligible computational over- head. We release all refined training data, training codes, pre-trained models and training logs 1 , which will help re- produce the results in this paper

12,694

社区成员

发帖
与我相关
我的任务
社区描述
CSDN 下载资源悬赏专区
其他 技术论坛(原bbs)
社区管理员
  • 下载资源悬赏专区社区
加入社区
  • 近7日
  • 近30日
  • 至今
社区公告
暂无公告

试试用AI创作助手写篇文章吧