Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groups

TL;DR

This paper investigates how training on different age groups affects the ability of models to recognize emotional facial expressions across ages, highlighting the importance of age diversity and domain generalisation techniques.

Contribution

It introduces a study of domain generalisation for emotional facial expression recognition across age groups, identifying effective algorithms and the impact of age-group diversity on performance.

Findings

CDANN performs best among tested algorithms.

Increasing age-group diversity improves unseen age-group recognition.

Excluding an age-group affects neighboring age-group performance.

Abstract

Apparent emotional facial expression recognition has attracted a lot of research attention recently. However, the majority of approaches ignore age differences and train a generic model for all ages. In this work, we study the effect of using different age-groups for training apparent emotional facial expression recognition models. To this end, we study Domain Generalisation in the context of apparent emotional facial expression recognition from facial imagery across different age groups. We first compare several domain generalisation algorithms on the basis of out-of-domain-generalisation, and observe that the Class-Conditional Domain-Adversarial Neural Networks (CDANN) algorithm has the best performance. We then study the effect of variety and number of age-groups used during training on generalisation to unseen age-groups and observe that an increase in the number of training age-groups tends to increase the apparent emotional facial expression recognition performance on unseen age-groups. We also show that exclusion of an age-group during training tends to affect more the performance of the neighbouring age groups.