Sorry, you need to enable JavaScript to visit this website.

Face Alignment by Deep Convolutional Network with Adaptive Learning Rate

Citation Author(s):
Zhiwen Shao, Shouhong Ding, Hengliang Zhu, Chengjie Wang, Lizhuang Ma
Submitted by:
Zhiwen Shao
Last updated:
19 March 2016 - 6:38am
Document Type:
Presentation Slides
Document Year:
Zhiwen Shao


Deep convolutional network has been widely used in face recognition while not often used in face alignment. One of the most important reasons of this is the lack of training images annotated with landmarks due to fussy and time-consuming annotation work. To overcome this problem, we propose a novel data augmentation strategy. And we design an innovative training algorithm with adaptive learning rate for two iterative procedures, which helps the network to search an optimal solution. Our convolutional network can learn global high-level features and directly predict the coordinates of facial landmarks. Extensive evaluations show that our approach outperforms state-of-the-art methods especially in the condition of complex occlusion, pose, illumination and expression variations.

0 users have voted: