Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing
This work addresses the need for more generalizable facial expression recognition systems for practical applications, representing an incremental improvement over existing methods.
The paper tackles the problem of limited generalizability in facial expression recognition systems by introducing Bounded Residual Gradient Networks (BReG-Net), which replace shortcut connections with a differentiable function to prevent gradient issues and use a weighted loss function, achieving state-of-the-art performance on three public databases.
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.