Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing
arXiv:1903.02110 · doi:10.1109/FG.2019.8756587
Abstract
Residual-based neural networks have shown remarkable results in various visual recognition tasks including Facial Expression Recognition (FER). Despite the tremendous efforts have been made to improve the performance of FER systems using DNNs, existing methods are not generalizable enough for practical applications. This paper introduces Bounded Residual Gradient Networks (BReG-Net) for facial expression recognition, in which the shortcut connection between the input and the output of the ResNet module is replaced with a differentiable function with a bounded gradient. This configuration prevents the network from facing the vanishing or exploding gradient problem. We show that utilizing such non-linear units will result in shallower networks with better performance. Further, by using a weighted loss function which gives a higher priority to less represented categories, we can achieve an overall better recognition rate. The results of our experiments show that BReG-Nets outperform state-of-the-art methods on three publicly available facial databases in the wild, on both the categorical and dimensional models of affect.
To appear in 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
- Going Deeper in Facial Expression Recognition using Deep Neural Networks
- Deep Learning using Linear Support Vector Machines
- Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
- Identity Mappings in Deep Residual Networks
- Self-supervised learning of a facial attribute embedding from video
- AVEC 2016 - Depression, Mood, and Emotion Recognition Workshop and Challenge
- Facial Expression Recognition from World Wild Web
- Facial Affect Estimation in the Wild Using Deep Residual and Convolutional Networks