Multi-task convolution network for face alignment
Open Access
- 1 August 2017
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 887 (1) , 012079
Abstract
In order to solve face alignment more effectively, we proposed a multi-task deep convolution network for face alignment, which achieves good performance even in the case of large pose variations and severe occlusion. Instead of dealing with face alignment as a single task, we jointly trained the auxiliary task of pose estimation together with face alignment to guide the distribution of facial points. By doing so we are able to 1) avoid trapping in the local optimum due to the inaccurate face boxes, 2) improve the robustness in dealing with faces with pose variation and severe occlusion. Compared with the traditional methods, our method also improves the accuracy by providing better initialization instead of mean shape. Extensive experiments show that our method has great performance on various benchmarks.Keywords
This publication has 21 references indexed in Scilit:
- Multi-task convolution network for face alignmentJournal of Physics: Conference Series, 2017
- Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment2014
- Facial Landmark Detection by Deep Multi-task Learning2014
- Face Alignment by Explicit Shape RegressionInternational Journal of Computer Vision, 2013
- Robust and Accurate Shape Model Fitting Using Random Forest Regression Voting2012
- Interactive Facial Feature Localization2012
- Localizing parts of faces using a consensus of exemplars2011
- Random ForestsMachine Learning, 2001
- Active appearance modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Multitask LearningMachine Learning, 1997