Reconstruction-Based Disentanglement for Pose-invariant Face Recognition

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)(2017)

引用 182|浏览102
暂无评分
摘要
Deep neural networks (DNNs) trained on large-scale datasets have recently achieved impressive improvements in face recognition. But a persistent challenge remains to develop methods capable of handling large pose variations that are relatively underrepresented in training data. This paper presents a method for learning a feature representation that is invariant to pose, without requiring extensive pose coverage in training data. We first propose to generate non-frontal views from a single frontal face, in order to increase the diversity of training data while preserving accurate facial details that are critical for identity discrimination. Our next contribution is to seek a rich embedding that encodes identity features, as well as non-identity ones such as pose and landmark locations. Finally, we propose a new feature reconstruction metric learning to explicitly disentangle identity and pose, by demanding alignment between the feature reconstructions through various combinations of identity and pose features, which is obtained from two images of the same subject. Experiments on both controlled and in-the-wild face datasets, such as MultiPIE, 300WLP and the profile view database CFP, show that our method consistently outperforms the state-of-the-art, especially on images with large head pose variations. Detail results and resource are referred to https://sites.google.com/site/xipengcshomepage/iccv2017
更多
查看译文
关键词
feature representation,nonfrontal views,identity discrimination,identity features,feature reconstruction metric learning,explicitly disentangle identity,in-the-wild face datasets,pose-invariant face recognition,deep neural networks,pose variations,pose coverage,facial details,Reconstruction-based disentanglement,frontal face,pose features
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要