通过分组对比学习提升人脸识别公平性，尤其改善低误匹配率下的弱势群体表现。
Bias Mitigation in Face Recognition via Demographic-based Supervised Contrastive Learning
- 设计按人口统计学分组的训练批次与配对策略，增强模型对弱势群体的区分能力。
- 在低误匹配率场景下，对性别、年龄、种族等群体的识别误差显著降低。
- 适合关注人脸识别公平性、部署于高安全场景的研究者与工程师。
人脸识别系统在不同性别、年龄或种族群体间表现出差异化的错误率，存在显著偏见。尽管训练数据的人口统计不平衡是原因之一，仅通过人工平衡数据集无法完全缓解该问题。实际应用中，人脸识别常运行在极低误匹配率的阈值点，即非匹配分数分布的尾部。虽然类别平衡能改善分布均值，但本研究聚焦于尾部行为的公平性优化。为此提出基于人口统计学的监督对比损失（DeSCon），通过精心设计的批量组成和人口统计感知的样本配对机制实现。在带有标注的人口统计学数据集及标准验证基准上的实验表明，DeSCon在保持竞争力验证性能的同时，显著提升了各群体间的公平性表现。代码可应要求提供。
原文摘要 · Abstract (English)
Face recognition systems have been shown to be biased toward certain demographic groups by exhibiting different error rates across gender, age, or ethnicity. Though the imbalance of the training data with respect to these demographics is one cause of this bias, training on artificially balanced groups does not completely mitigate the problem. For deployment, face recognition typically works at operating points allowing very low false match rates and, hence, on the tail of the non-match score distribution. While class balancing can improve the means of these distributions, the aim of our approach is to improve fairness by addressing the behavior in the tail. Particularly, we propose the Demographic-based Supervised Contrastive loss (DeSCon) for face recognition, which relies on a well-designed composition of training batches and demographic-aware pair selection. Our experimental evaluation on both demographically-labeled datasets and standard verification benchmarks shows that DeSCon can improve fairness beyond balancing training datasets while maintaining competitive verification performance. Source code is available upon request.
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。