CorrLoss: Integrating Co-Occurrence Domain Knowledge for Affect Recognition
This work addresses the need for more generalizable and less overfitted models in affect recognition, though it appears incremental as it builds on existing neural network methods with a specific constraint.
The paper tackled the problem of underutilizing domain knowledge in neural networks for affect recognition by integrating co-occurrence patterns of facial movements as a loss constraint, resulting in improved cross-dataset performance and reduced overfitting.
Neural networks are widely adopted, yet the integration of domain knowledge is still underutilized. We propose to integrate domain knowledge about co-occurring facial movements as a constraint in the loss function to enhance the training of neural networks for affect recognition. As the co-ccurrence patterns tend to be similar across datasets, applying our method can lead to a higher generalizability of models and a lower risk of overfitting. We demonstrate this by showing performance increases in cross-dataset testing for various datasets. We also show the applicability of our method for calibrating neural networks to different facial expressions.