无需属性标签，通过动态调整学习参数提升人脸识别公平性。
LabellessFace: Fair Metric Learning for Face Recognition without Attribute Labels
- 提出类偏袒度指标，量化数据集中对特定类别的偏好程度。
- 设计公平类间距惩罚，根据偏袒度动态调整训练参数。
- 在不依赖标签情况下有效降低识别偏差，适合公平性研究者。
性别与种族等人口统计学偏差是人脸识别系统面临的主要挑战。现有多数研究高度依赖特定人口群体或人口分类器，难以解决未被识别群体的性能问题。本文提出「LabellessFace」框架，可在无需人口统计学标签的情况下改善人脸识别中的公平性。我们引入一种新的公平性增强度量——类偏袒度，用于评估数据集中对特定类别存在的偏好程度。基于该度量，提出公平类间距惩罚，作为现有基于间距的度量学习方法的扩展。该方法根据类偏袒度动态调节学习参数，促进所有属性下的公平表现。通过将每个类别视为独立个体，实现认证准确率中偏见最小化的学习。大量实验表明，所提方法在保持认证准确率的同时，有效提升了公平性。
原文摘要 · Abstract (English)
Demographic bias is one of the major challenges for face recognition systems. The majority of existing studies on demographic biases are heavily dependent on specific demographic groups or demographic classifier, making it difficult to address performance for unrecognised groups. This paper introduces ``LabellessFace'', a novel framework that improves demographic bias in face recognition without requiring demographic group labeling typically required for fairness considerations. We propose a novel fairness enhancement metric called the class favoritism level, which assesses the extent of favoritism towards specific classes across the dataset. Leveraging this metric, we introduce the fair class margin penalty, an extension of existing margin-based metric learning. This method dynamically adjusts learning parameters based on class favoritism levels, promoting fairness across all attributes. By treating each class as an individual in facial recognition systems, we facilitate learning that minimizes biases in authentication accuracy among individuals. Comprehensive experiments have demonstrated that our proposed method is effective for enhancing fairness while maintaining authentication accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。