Effective face landmark localization via single deep network
This addresses face landmark localization for computer vision applications, but it appears incremental as it builds on existing CNN methods with modifications.
The paper tackles face alignment by proposing a single deep network with stacked layer groups and data augmentation, achieving state-of-the-art results in accuracy and speed on COFW and 300-W datasets.
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 max-pooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to over-come the lack of training images on COFW and 300-W da-tasets. The experiment results show that our method outper-forms state-of-the-art methods in both detection accuracy and speed.