Emotion Recognition with Facial Attention and Objective Activation Functions
This work addresses emotion recognition accuracy for computer vision applications, but it is incremental as it applies known attention mechanisms to existing models.
The paper tackled facial emotion recognition by introducing channel and spatial attention mechanisms (SEN-Net, ECA-Net, CBAM) to existing CNN models (VGGNet, ResNet, ResNetV2) and combining them with different activation functions, resulting in significant performance improvements.
In this paper, we study the effect of introducing channel and spatial attention mechanisms, namely SEN-Net, ECA-Net, and CBAM, to existing CNN vision-based models such as VGGNet, ResNet, and ResNetV2 to perform the Facial Emotion Recognition task. We show that not only attention can significantly improve the performance of these models but also that combining them with a different activation function can further help increase the performance of these models.