# Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing

## TL;DR

This paper introduces BReG-Net, a novel neural network architecture with bounded residual gradients for improved facial expression recognition, addressing gradient issues and class imbalance to outperform existing methods on multiple datasets.

## Contribution

The paper proposes BReG-Net with bounded residual gradients and a weighted loss function, enhancing generalization and performance in facial affect recognition tasks.

## Key findings

- BReG-Net outperforms state-of-the-art methods on three facial databases.
- Bounded residual gradients enable shallower networks with better accuracy.
- Weighted loss improves recognition of underrepresented categories.

## 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.