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

2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)(2019)

引用 8|浏览15
暂无评分
摘要
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.
更多
查看译文
关键词
BReG-Net,Residual-based neural networks,visual recognition tasks,facial expression recognition,FER systems,shallower networks,recognition rate,publicly available facial databases,bounded residual gradient networks,facial affect computing,weighted loss function
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要