CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Efficient Face Alignment with Fast Normalization and Contour Fitting Loss
Liu, Zhiwei1,2; Zhu, Xiangyu1,2; Tang, Ming1,2; Lei, Zhen1,2; Wang, Jinqiao1,2
Source PublicationACM Transactions on Multimedia Computing, Communications, and Applications
2019-10
Issue3Pages:16
Abstract

Face alignment is a key component of numerous face analysis tasks. In recent years, most existing methods have focused on designing high-performance face alignment systems and paid less attention to efficiency.
However more face alignment systems are now applied on low-cost devices, such as mobile phones. In this article, we design a common efficient framework that can team with any face alignment regression network and improve the overall performance with nearly no extra computational cost. First, we discover that the maximum regression error exists in the face contour, where landmarks do not have distinct semantic positions, and thus are randomly labeled along the face contours in training data. To address this problem, we propose a novel contour fitting loss that dynamically adjusts the regression target during training so the
network can learn more accurate semantic meanings of the contour landmarks and achieve better localization performance. Second, we decouple the complex sample variations in face alignment task and propose a Fast Normalization Module (FNM) to efficiently normalize considerable variations that can be described by geometric transformation. Finally, a new lightweight network architecture named Lightweight Alignment Module (LAM) is also proposed to achieve fast and precise face alignment on mobile devices. Our method achieves competitive performance with state-of-the-arts on 300W and AFLW2000-3D benchmarks. Meanwhile, the speed of our framework is significantly faster than other CNN-based approaches.

KeywordFace alignment, convolutional neural networks, real-time, semantic meaning
Indexed BySCI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/40392
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.中国科学院自动化研究所模式识别国家重点实验室
2.中国科学院大学
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Liu, Zhiwei,Zhu, Xiangyu,Tang, Ming,et al. Efficient Face Alignment with Fast Normalization and Contour Fitting Loss[J]. ACM Transactions on Multimedia Computing, Communications, and Applications,2019(3):16.
APA Liu, Zhiwei,Zhu, Xiangyu,Tang, Ming,Lei, Zhen,&Wang, Jinqiao.(2019).Efficient Face Alignment with Fast Normalization and Contour Fitting Loss.ACM Transactions on Multimedia Computing, Communications, and Applications(3),16.
MLA Liu, Zhiwei,et al."Efficient Face Alignment with Fast Normalization and Contour Fitting Loss".ACM Transactions on Multimedia Computing, Communications, and Applications .3(2019):16.
Files in This Item: Download All
File Name/Size DocType Version Access License
代表性论文2-刘智威.pdf(1359KB)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
[Liu, Zhiwei]'s Articles
[Zhu, Xiangyu]'s Articles
[Tang, Ming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Zhiwei]'s Articles
[Zhu, Xiangyu]'s Articles
[Tang, Ming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Zhiwei]'s Articles
[Zhu, Xiangyu]'s Articles
[Tang, Ming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 代表性论文2-刘智威.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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