Balancing the Scales: Enhancing Fairness in Facial Expression Recognition with Latent Alignment
It addresses fairness issues in FER, an important domain for emotion analysis, but is incremental as bias mitigation has been explored in other areas.
The paper tackles bias in facial expression recognition (FER) datasets, which arise from manual annotation and demographic imbalances, by using latent space representation learning to enhance fairness and accuracy.
Automatically recognizing emotional intent using facial expression has been a thoroughly investigated topic in the realm of computer vision. Facial Expression Recognition (FER), being a supervised learning task, relies heavily on substantially large data exemplifying various socio-cultural demographic attributes. Over the past decade, several real-world in-the-wild FER datasets that have been proposed were collected through crowd-sourcing or web-scraping. However, most of these practically used datasets employ a manual annotation methodology for labeling emotional intent, which inherently propagates individual demographic biases. Moreover, these datasets also lack an equitable representation of various socio-cultural demographic groups, thereby inducing a class imbalance. Bias analysis and its mitigation have been investigated across multiple domains and problem settings, however, in the FER domain, this is a relatively lesser explored area. This work leverages representation learning based on latent spaces to mitigate bias in facial expression recognition systems, thereby enhancing a deep learning model's fairness and overall accuracy.