Deep Regression for Face Alignment
This addresses face alignment for computer vision applications, but appears incremental as it builds on existing deep regression methods.
The paper tackles face alignment by proposing a deep regression approach with global and multi-stage local layers, achieving state-of-the-art results in experiments.
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