Effective face landmark localization via single deep network

In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a maxpooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to overcome the lack of training images on COFW and 300-W datasets. The experiment results show that our method outperforms stateof-the-art methods in both detection accuracy and speed.