Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency
This addresses fairness and consistency issues in affect recognition for researchers, though it is incremental as it focuses on evaluation protocols rather than new methods.
The paper tackles the problem of inconsistent and biased evaluation in affect analysis by proposing a unified protocol for database partitioning that ensures fairness and comparability, resulting in new leaderboards and publicly available annotations, code, and pre-trained models.
Evaluating affect analysis methods presents challenges due to inconsistencies in database partitioning and evaluation protocols, leading to unfair and biased results. Previous studies claim continuous performance improvements, but our findings challenge such assertions. Using these insights, we propose a unified protocol for database partitioning that ensures fairness and comparability. We provide detailed demographic annotations (in terms of race, gender and age), evaluation metrics, and a common framework for expression recognition, action unit detection and valence-arousal estimation. We also rerun the methods with the new protocol and introduce a new leaderboards to encourage future research in affect recognition with a fairer comparison. Our annotations, code, and pre-trained models are available on \hyperlink{https://github.com/dkollias/Fair-Consistent-Affect-Analysis}{Github}.