5 papers
Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models
Ãnsal Ãztürk, Sébastien Marcel
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 th…
Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition
Ãnsal Ãztürk, Vedrana KrivokuÄa Hahn, Sushil Bhattacharjee +1
Face recognition embeddings encode identity, but they also encode other factors such as gender and ethnicity. Depending on how these factors are used by a downstream system, separa…
Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition
Behrooz Razeghi, Parsa Rahimi, Sébastien Marcel
In this study, we apply the information-theoretic Privacy Funnel (PF) model to face recognition and develop a method for privacy-preserving representation learning within an end-to…
ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition
Parsa Rahimi, Sebastien Marcel
Synthetic data generation is increasingly used in machine learning for training and data augmentation. Yet, current strategies often rely on external foundation models or datasets,…
AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition
Parsa Rahimi, Damien Teney, Sebastien Marcel
The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Sy…