Deep Regression for Face Alignment

Abstract

In this paper, we present a deep regression approach for face alignment. The deep architecture consists of a global layer and multi-stage local layers. We apply the back-propagation algorithm with the dropout strategy to jointly optimize the regression parameters. We show that the resulting deep regressor gradually and evenly approaches the true facial landmarks stage by stage, avoiding the tendency to yield over-strong early stage regressors while over-weak later stage regressors. Experimental results show that our approach achieves the state-of-the-art

References in corpus (1)

• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (4)

• Learning Deep Representation for Face Alignment with Auxiliary Attributes
• Quantized Densely Connected U-Nets for Efficient Landmark Localization
• Globally Tuned Cascade Pose Regression via Back Propagation with Application in 2D Face Pose Estimation and Heart Segmentation in 3D CT Images
• A fast online cascaded regression algorithm for face alignment