论文标题
CAT：公平面部属性分类的可控属性翻译
CAT: Controllable Attribute Translation for Fair Facial Attribute Classification
论文作者
论文摘要
由于视觉识别的社会影响一直受到审查，因此出现了几个受保护的平衡数据集，以解决不平衡数据集中的数据集偏差。但是，在面部属性分类中，数据集偏差既源于受保护的属性级别和面部属性级别，这使得构建多属性级别平衡的真实数据集使其具有挑战性。为了弥合差距，我们提出了一条有效的管道，以产生具有所需面部属性的高质量和足够的面部图像，并将原始数据集补充为两个级别的平衡数据集，从理论上讲，这在理论上满足了几个公平标准。我们的方法的有效性在性别分类和面部属性分类方面得到了验证，该任务性能与原始数据集相当，并在具有广泛的指标的全面公平评估中进一步提高公平性。此外，我们的方法的表现优于重采样和平衡的数据集构建，以解决数据集偏差，以及对任务偏差的偏见模型。
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.
