论文标题
通过图像特征解释深面识别的偏见
Explaining Bias in Deep Face Recognition via Image Characteristics
论文作者
论文摘要
在本文中，我们提出了一个新颖的解释性框架，旨在更好地理解面部识别模型作为基础数据特征的表现（受保护的属性：性别，种族，年龄，年龄；非保护属性：面部毛发，化妆品，配件，配件，脸部方向和遮挡，图像失真，情绪），这些属性已被测试。通过我们的框架，我们评估了十种最先进的面部识别模型，并在两个数据集的安全性和可用性方面进行了比较，涉及基于性别和种族的六个组。然后，我们分析图像特征对模型性能的影响。我们的结果表明，当考虑多属性组时，单属分析中出现的趋势消失或逆转，并且性能差异也与非保护属性有关。源代码：https：//cutt.ly/2xwrlia。
In this paper, we propose a novel explanatory framework aimed to provide a better understanding of how face recognition models perform as the underlying data characteristics (protected attributes: gender, ethnicity, age; non-protected attributes: facial hair, makeup, accessories, face orientation and occlusion, image distortion, emotions) on which they are tested change. With our framework, we evaluate ten state-of-the-art face recognition models, comparing their fairness in terms of security and usability on two data sets, involving six groups based on gender and ethnicity. We then analyze the impact of image characteristics on models performance. Our results show that trends appearing in a single-attribute analysis disappear or reverse when multi-attribute groups are considered, and that performance disparities are also related to non-protected attributes. Source code: https://cutt.ly/2XwRLiA.
