Benchmarking Face Recognition without Real Faces
Merged summary
TL;DR - This arXiv paper asks whether synthetic face datasets can replace real-face benchmarks for evaluating face recognition, showing the best synthetic sets can support reliable comparative evaluation and enable a fully privacy-preserving pipeline.
- Tested 12 synthetic datasets against 7 established real benchmarks using 24 pre-trained models spanning CNN and transformer architectures.
- Evaluation spanned biometric verification metrics, similarity score distributions, cross-model ranking consistency, and each dataset's distributional properties.
- MorphFace and Vec2Face were strongest, reproducing real benchmarks' relative behavior within the natural disagreement already seen among real benchmarks themselves.
- Motivation: synthetic training already rivals real-photo accuracy, but reliance on real-face evaluation left the privacy problem only "half solved."
Sources (1)
Benchmarking Face Recognition without Real Faces
TL;DR - This arXiv paper asks whether synthetic face datasets can replace real-face benchmarks for evaluating face recognition, showing the best synthetic sets can support reliable comparative evaluation and enable a fully privacy-preserving pipeline.
- Tested 12 synthetic datasets against 7 established real benchmarks using 24 pre-trained models spanning CNN and transformer architectures.
- Evaluation spanned biometric verification metrics, similarity score distributions, cross-model ranking consistency, and each dataset's distributional properties.
- MorphFace and Vec2Face were strongest, reproducing real benchmarks' relative behavior within the natural disagreement already seen among real benchmarks themselves.
- Motivation: synthetic training already rivals real-photo accuracy, but reliance on real-face evaluation left the privacy problem only "half solved."