FunFace: Feature Utility and Norm Estimation for Face Recognition

arXiv cs.CV / 4/30/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes FunFace, a new adaptive margin loss for face recognition that explicitly estimates feature norm utility rather than relying only on general image quality proxies.
It incorporates biometric utility via the Certainty Ratio into the margin computation, building on the AdaFace approach but shifting the utility signal toward FIQA-driven metrics.
The authors argue that feature norms correlate with biometric utility only partially, motivating a loss function that better captures additional utility factors.
Experiments show FunFace training yields competitive performance on benchmarks with high-quality samples and outperforms existing state-of-the-art methods on low-quality benchmarks.
Overall, FunFace aims to improve robustness of face recognition models across challenging real-world capture conditions by better aligning training objectives with sample usefulness.

Abstract

Face Recognition (FR) is used in a variety of application domains, from entertainment and banking to security and surveillance. Such applications rely on the FR model to be robust and perform well in a variety of settings. To achieve this, state-of-the-art FR models typically use expressive adaptive margin loss functions, which tie the feature norm to concepts related to sample quality, such as recognizability and perceptual image quality. Recently, through the development of Face Image Quality Assessment (FIQA) techniques, biometric utility has become the preferred measure of face-image quality and has been shown to be a better predictor of the usefulness of samples for face recognition compared to more human-centric aspects, such as resolution, blur, and lighting, tied to general image quality. While image quality expressed through feature norms exhibits a certain level of correlation with biometric utility, it does not fully encapsulate all aspects of utility. To address this point, we propose a new adaptive margin loss, FunFace (Face Recognition Through Utility and Norm Estimation), which incorporates biometric utility, estimated by the Certainty Ratio, into the adaptive margin, taking inspiration from AdaFace. We show that FunFace (when used to train a face recognition model) achieves competitive results to other state-of-the-art FR models on benchmarks containing high-quality samples, while surpassing them on low quality benchmarks.