Domain Adaptation for Facial Expression Classifier via Domain Discrimination and Gradient Reversal

TL;DR

This paper introduces a new facial expression recognition architecture that leverages domain discrimination loss regularization to improve performance across different domains, enhancing human-computer interaction capabilities.

Contribution

It proposes a novel FER architecture incorporating domain discrimination and gradient reversal, advancing domain adaptation techniques for facial expression recognition.

Findings

Improved accuracy in cross-domain FER tasks

Effective integration of domain discrimination loss regularization

Potential for enhanced human-computer interaction applications

Abstract

Bringing empathy to a computerized system could significantly improve the quality of human-computer communications, as soon as machines would be able to understand customer intentions and better serve their needs. According to different studies (Literature Review), visual information is one of the most important channels of human interaction and contains significant behavioral signals, that may be captured from facial expressions. Therefore, it is consistent and natural that the research in the field of Facial Expression Recognition (FER) has acquired increased interest over the past decade due to having diverse application area including health-care, sociology, psychology, driver-safety, virtual reality, cognitive sciences, security, entertainment, marketing, etc. We propose a new architecture for the task of FER and examine the impact of domain discrimination loss regularization on the learning process. With regard to observations, including both classical training conditions and unsupervised domain adaptation scenarios, important aspects of the considered domain adaptation approach integration are traced. The results may serve as a foundation for further research in the field.