ComboLoss for Facial Attractiveness Analysis with Squeeze-and-Excitation Networks
This work addresses the problem of improving facial attractiveness analysis for applications in computer vision, but it is incremental as it focuses on loss function optimization within an existing framework.
The paper tackles facial attractiveness recognition by proposing a novel loss function called ComboLoss, which achieves state-of-the-art performance with improvements of 1.13%, 2.1%, and 0.57% on three datasets compared to prior methods.
Loss function is crucial for model training and feature representation learning, conventional models usually regard facial attractiveness recognition task as a regression problem, and adopt MSE loss or Huber variant loss as supervision to train a deep convolutional neural network (CNN) to predict facial attractiveness score. Little work has been done to systematically compare the performance of diverse loss functions. In this paper, we firstly systematically analyze model performance under diverse loss functions. Then a novel loss function named ComboLoss is proposed to guide the SEResNeXt50 network. The proposed method achieves state-of-the-art performance on SCUT-FBP, HotOrNot and SCUT-FBP5500 datasets with an improvement of 1.13%, 2.1% and 0.57% compared with prior arts, respectively. Code and models are available at https://github.com/lucasxlu/ComboLoss.git.