新指标CEI能精准检测人脸识别中的细微偏见，尤其擅长发现尾部差异。
Balancing Tails when Comparing Distributions: Comprehensive Equity Index (CEI) with Application to Bias Evaluation in Operational Face Biometrics
- 分别分析真实与伪造分数分布，可调节关注尾部概率
- 在多种数据集和模型上验证，比旧方法更敏感地发现隐性偏见
- 支持自动化评估，适合实际部署中的公平性审查
高性能人脸识别系统中的群体偏见常被现有度量方法忽略，尤其是分数分布尾部的细微差异。本文提出综合公平指数（CEI），通过分别分析真实与伪造分数分布，可在配置下聚焦尾部概率，同时考虑整体分布形态。大量实验（涵盖顶尖FR系统、故意引入偏见的模型及多样化数据集）表明，CEI在检测复杂偏见方面显著优于传统方法。此外，我们提出自动化版本CEI^A，提升评估客观性并简化应用。该方法专为人脸识别偏见评估设计，但也可推广至任何关注分布尾部的统计比较问题。
原文摘要 · Abstract (English)
Demographic bias in high-performance face recognition (FR) systems often eludes detection by existing metrics, especially with respect to subtle disparities in the tails of the score distribution. We introduce the Comprehensive Equity Index (CEI), a novel metric designed to address this limitation. CEI uniquely analyzes genuine and impostor score distributions separately, enabling a configurable focus on tail probabilities while also considering overall distribution shapes. Our extensive experiments (evaluating state-of-the-art FR systems, intentionally biased models, and diverse datasets) confirm CEI's superior ability to detect nuanced biases where previous methods fall short. Furthermore, we present CEI^A, an automated version of the metric that enhances objectivity and simplifies practical application. CEI provides a robust and sensitive tool for operational FR fairness assessment. The proposed methods have been developed particularly for bias evaluation in face biometrics but, in general, they are applicable for comparing statistical distributions in any problem where one is interested in analyzing the distribution tails.
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。