Bridging the Gap: Protocol Towards Fair and Consistent Affect Analysis

TL;DR

This paper proposes a standardized protocol for affect analysis to improve fairness and consistency across diverse demographic groups, addressing biases and evaluation disparities in existing datasets and methods.

Contribution

It introduces a common database partitioning protocol and demographic annotations, enhancing fairness and comparability in affect analysis research.

Findings

Demonstrates the impact of demographic considerations on affect analysis accuracy

Reveals inadequacies in prior evaluation methods due to dataset biases

Provides annotated databases, code, and models for equitable affect analysis

Abstract

The increasing integration of machine learning algorithms in daily life underscores the critical need for fairness and equity in their deployment. As these technologies play a pivotal role in decision-making, addressing biases across diverse subpopulation groups, including age, gender, and race, becomes paramount. Automatic affect analysis, at the intersection of physiology, psychology, and machine learning, has seen significant development. However, existing databases and methodologies lack uniformity, leading to biased evaluations. This work addresses these issues by analyzing six affective databases, annotating demographic attributes, and proposing a common protocol for database partitioning. Emphasis is placed on fairness in evaluations. Extensive experiments with baseline and state-of-the-art methods demonstrate the impact of these changes, revealing the inadequacy of prior assessments. The findings underscore the importance of considering demographic attributes in affect analysis research and provide a foundation for more equitable methodologies. Our annotations, code and pre-trained models are available at: https://github.com/dkollias/Fair-Consistent-Affect-Analysis