NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face Generation
This work addresses identity separability issues in synthetic face data for face recognition systems, representing an incremental improvement over existing identity-conditioned diffusion methods.
The paper tackles the problem of identity overlap in synthetic face generation by introducing NegFaceDiff, a sampling method that uses negative conditions to enhance identity separability, resulting in a Fisher Discriminant Ratio increase from 2.427 to 5.687 and improved face recognition performance.
The use of synthetic data as an alternative to authentic datasets in face recognition (FR) development has gained significant attention, addressing privacy, ethical, and practical concerns associated with collecting and using authentic data. Recent state-of-the-art approaches have proposed identity-conditioned diffusion models to generate identity-consistent face images, facilitating their use in training FR models. However, these methods often lack explicit sampling mechanisms to enforce inter-class separability, leading to identity overlap in the generated data and, consequently, suboptimal FR performance. In this work, we introduce NegFaceDiff, a novel sampling method that incorporates negative conditions into the identity-conditioned diffusion process. NegFaceDiff enhances identity separation by leveraging negative conditions that explicitly guide the model away from unwanted features while preserving intra-class consistency. Extensive experiments demonstrate that NegFaceDiff significantly improves the identity consistency and separability of data generated by identity-conditioned diffusion models. Specifically, identity separability, measured by the Fisher Discriminant Ratio (FDR), increases from 2.427 to 5.687. These improvements are reflected in FR systems trained on the NegFaceDiff dataset, which outperform models trained on data generated without negative conditions across multiple benchmarks.