CAT: Controllable Attribute Translation for Fair Facial Attribute Classification
This addresses fairness issues in facial recognition for affected populations, though it is incremental as it builds on existing balanced dataset methods.
The paper tackles dataset bias in facial attribute classification by proposing a pipeline to generate balanced facial images with desired attributes, achieving comparable task performance to the original dataset and improving fairness across multiple metrics.
As the social impact of visual recognition has been under scrutiny, several protected-attribute balanced datasets emerged to address dataset bias in imbalanced datasets. However, in facial attribute classification, dataset bias stems from both protected attribute level and facial attribute level, which makes it challenging to construct a multi-attribute-level balanced real dataset. To bridge the gap, we propose an effective pipeline to generate high-quality and sufficient facial images with desired facial attributes and supplement the original dataset to be a balanced dataset at both levels, which theoretically satisfies several fairness criteria. The effectiveness of our method is verified on sex classification and facial attribute classification by yielding comparable task performance as the original dataset and further improving fairness in a comprehensive fairness evaluation with a wide range of metrics. Furthermore, our method outperforms both resampling and balanced dataset construction to address dataset bias, and debiasing models to address task bias.