Pairwise Discernment of AffectNet Expressions with ArcFace
This work addresses emotion recognition for human-computer interaction, but it is incremental as it builds on existing methods and datasets.
The study tackled facial emotion recognition by applying transfer learning with ResNeXt, EfficientNet, and ArcFace models on the AffectNet dataset, finding that pairwise learning helps address class imbalances to improve model performance.
This study takes a preliminary step toward teaching computers to recognize human emotions through Facial Emotion Recognition (FER). Transfer learning is applied using ResNeXt, EfficientNet models, and an ArcFace model originally trained on the facial verification task, leveraging the AffectNet database, a collection of human face images annotated with corresponding emotions. The findings highlight the value of congruent domain transfer learning, the challenges posed by imbalanced datasets in learning facial emotion patterns, and the effectiveness of pairwise learning in addressing class imbalances to enhance model performance on the FER task.