发现人脸模型嵌入空间受发型、肤色等属性影响，提出新方法解析其敏感性。
Attributes Shape the Embedding Space of Face Recognition Models
- 用几何方法分析模型对头发颜色、对比度等属性的依赖关系
- 不同属性下模型不变性差异明显，揭示其优缺点
- 适合关注模型可解释性和公平性的研究者参考
深度神经网络推动了人脸识别（FR）的发展，尤其依赖基于边距的三元组损失将人脸图像嵌入高维特征空间。训练中这类对比损失仅以身份信息为标签，但我们观察到嵌入空间中存在多尺度几何结构，受可解释的人脸属性（如发色）和图像属性（如对比度）影响。本文提出一种几何方法描述模型对这些属性的依赖或不变性，并引入受物理启发的对齐度量。在简化模型和使用合成数据微调的主流FR模型上评估该度量，结果表明模型对不同属性的不变性程度各异，揭示其内在特性并提升可解释性。代码已开源：https://github.com/mantonios107/attrs-fr-embs
原文摘要 · Abstract (English)
Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these contrastive losses focus exclusively on identity information as labels. However, we observe a multiscale geometric structure emerging in the embedding space, influenced by interpretable facial (e.g., hair color) and image attributes (e.g., contrast). We propose a geometric approach to describe the dependence or invariance of FR models to these attributes and introduce a physics-inspired alignment metric. We evaluate the proposed metric on controlled, simplified models and widely used FR models fine-tuned with synthetic data for targeted attribute augmentation. Our findings reveal that the models exhibit varying degrees of invariance across different attributes, providing insight into their strengths and weaknesses and enabling deeper interpretability. Code available here: https://github.com/mantonios107/attrs-fr-embs}{https://github.com/mantonios107/attrs-fr-embs
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。