Dynamic Noise Injection for Facial Expression Recognition In-the-Wild
Facial expression-based emotion analysis is one of the most important artificial intelligence research fields. However, a lot of works still suffer from the low classification/regression performance caused by overfitting. Therefore, this paper proposes a new noise injection technique to alleviate this problem. Specifically, based on the ResNet-18 architecture, we dynamically add feature-level noise into the BN+ReLU unit to learn more robust features. Experiments on facial expression classification with the AffectNet dataset demonstrated the usefulness of the proposed approach.