Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 46%Hugging Face Models on Foundry Managed Compute →
- LinkedLinked via arxiv author · 85%Ünsal Öztürk →
“Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models”
- LinkedLinked via arxiv author · 85%Sébastien Marcel →
“Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models”