Learning Late, Guiding Early: Timestep-Decoupled Semantic Guidance for Fair Face Generation
Semantic Boundary Predictor (SBP) is an inference-time method that guides synthetic face generation toward demographic fairness without retraining the underlying diffusion model. It works by learning linear semantic boundaries from late-stage latent representations and applying this guidance only once at the initial noisy step during reverse denoising. This approach successfully reduces demographic disparity significantly while preserving high image quality.