CRNet: Classification and Regression Neural Network for Facial Beauty Prediction

Facial beauty prediction is a challenging problem in computer vision and multimedia fields, due to the variant pose and diverse conditions. In this paper, we introduce “soft label” for each annotated facial image, and propose a novel neural network–classification and regression network (CRNet) with different branches, to simultaneously process a classification and a regression task. Besides, weighted mean squared error (MSE) and cross entropy (CE) are used as the loss function, which is robust to outliers. CRNet achieves state-of-the-art performance on SCUT-FBP and ECCV HotOrNot dataset. Experimental results demonstrate the effectiveness of the proposed method and clarify the most important facial regions for facial beauty perception.