Balanced synthetic face data from Stable Diffusion v3.5 reduces racial bias in face recognition models but does not yet match real-data accuracy on hard benchmarks.
Digi2Real: Bridging the realism gap in synthetic-data face recognition via foundation models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Data
Balanced synthetic face data from Stable Diffusion v3.5 reduces racial bias in face recognition models but does not yet match real-data accuracy on hard benchmarks.