Evaluating Facial Expression Recognition Datasets for Deep Learning: A Benchmark Study with Novel Similarity Metrics
It addresses dataset selection challenges for researchers and practitioners in affective computing, offering incremental improvements through new metrics and analysis.
This study evaluated 24 facial expression recognition datasets for deep learning, introducing novel similarity metrics to assess difficulty and generalization, and found that large-scale datasets generalize better despite noise, while controlled ones have higher quality but less variability.
This study investigates the key characteristics and suitability of widely used Facial Expression Recognition (FER) datasets for training deep learning models. In the field of affective computing, FER is essential for interpreting human emotions, yet the performance of FER systems is highly contingent on the quality and diversity of the underlying datasets. To address this issue, we compiled and analyzed 24 FER datasets, including those targeting specific age groups such as children, adults, and the elderly, and processed them through a comprehensive normalization pipeline. In addition, we enriched the datasets with automatic annotations for age and gender, enabling a more nuanced evaluation of their demographic properties. To further assess dataset efficacy, we introduce three novel metricsLocal, Global, and Paired Similarity, which quantitatively measure dataset difficulty, generalization capability, and cross-dataset transferability. Benchmark experiments using state-of-the-art neural networks reveal that large-scale, automatically collected datasets (e.g., AffectNet, FER2013) tend to generalize better, despite issues with labeling noise and demographic biases, whereas controlled datasets offer higher annotation quality but limited variability. Our findings provide actionable recommendations for dataset selection and design, advancing the development of more robust, fair, and effective FER systems.