发表机构
Idiap Research Institute; Université de Lausanne (UNIL)（Idiap研究所; 洛桑大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究在人脸识别模型超球面嵌入几何中量化训练成员信息，通过计算基于聚类几何的四个统计量，分析训练因素对成员/非成员可分离性的影响，还分析跨域情况，最后融合统计量与分类器揭示更多成员信息。
AI 中文摘要
人脸识别模型通过对相同身份的嵌入进行聚类，同时通过角度边缘损失将不同身份推开，将每张脸表示为单位超球面上的嵌入向量。由于这些损失仅作用于训练身份，非成员身份可能形成具有不同几何属性的聚类。本文量化了这种差异的大小以及训练时的哪些因素控制它。我们基于聚类几何计算了四个统计量，在IResNet骨干网络大小、损失头、训练持续时间和训练身份数量的析因设计中，对180个人脸识别模型进行计算，并在九个基准上评估每个配置。结果表明，训练身份的数量对成员/非成员可分离性影响最大，而骨干网络和损失头的贡献要小得多，并且在同一域保留参考上，随着更多身份添加到训练中，几何成员信号单调下降。我们对跨域（姿势、年龄、质量、种族）非成员基准进行了分析，并报告这些会夸大明显的成员信号。最后，我们将所有四个统计量与一个学习到的分类器融合，以揭示超出最佳单个统计量的额外成员信息。
英文摘要
Face recognition models represent each face as an embedding vector on the unit hypersphere by clustering embeddings of the same identity while pushing different identities apart through angular-margin losses. Because these losses act only on training identities, non-member identities may form clusters with different geometric properties. In this paper, we quantify the magnitude of this difference and what training-time factors control it. We compute four statistics based on cluster geometry across 180 face recognition models in a factorial design over IResNet backbone size, loss head, training duration, and the number of training identities, and evaluate each configuration on nine benchmarks. Our results indicate that the number of training identities has the largest effect on member/non-member separability, while backbone and loss head contribute far less, and that, on a same-domain held-out reference, the geometric membership signal decreases monotonically as more identities are added to training. We provide an analysis of cross-domain (pose, age, quality, ethnicity) non-member benchmarks and report that these inflate the apparent membership signal. Finally, we fuse all four statistics with a learned classifier to reveal additional membership information beyond the best individual statistic.
CommentsAccepted at IEEE/IAPR IJCB 2026
