Residual Neural Network and Wing Loss for Face Alignment Network

Face recognition has made great progress due to the development of convolutional neural network (CNN), and face alignment is an important part of recognition, it is easily affected by gestures and occlusion. In this paper, we propose Residual Neural Network and Wing Loss for Face Alignment Network (RWAN), which consists of a plurality of stages, each stage ameliorates the position of facial landmarks estimated from the previous stage. Unlike the traditional cascading model, the network model uses the Residual Neural Network, which is easily to optimize and can improve accuracy by adding considerable depth, the internal residual block uses shortcut to alleviate the gradient explosion problem caused by increasing depth in deep neural network. Enter the face images and extract features from the entire image by introducing landmark heatmaps to obtain more accurate positioning. Using wing loss in the loss function part not only focuses on the landmark of large error points, but also on the small and medium errors of landmarks, it aims to improve the training ability of deep neural network with small and medium range error. The problem of unbalanced data not only confuses classification tasks, but also affects the accuracy of the model when face samples of different attitudes are not balanced in face key detection tasks. a simple but effective data enhancement method is proposed to deal with the problem, which solves the problem of unbalanced data processing by randomly rotating the training samples, amplifying and the like. The experimental results obtained by our method on the 300W dataset indicate the advantages of this method.