Data Uncertainty Learning in Face Recognition
This work addresses noisy face recognition for applications like surveillance or biometrics, representing an incremental advance by building on prior uncertainty modeling.
The paper tackles the problem of data uncertainty in face recognition by simultaneously learning feature embeddings and uncertainty estimates, achieving improved performance over existing deterministic methods and the prior uncertainty-aware approach PFE on challenging unconstrained scenarios.
Modeling data uncertainty is important for noisy images, but seldom explored for face recognition. The pioneer work, PFE, considers uncertainty by modeling each face image embedding as a Gaussian distribution. It is quite effective. However, it uses fixed feature (mean of the Gaussian) from an existing model. It only estimates the variance and relies on an ad-hoc and costly metric. Thus, it is not easy to use. It is unclear how uncertainty affects feature learning. This work applies data uncertainty learning to face recognition, such that the feature (mean) and uncertainty (variance) are learnt simultaneously, for the first time. Two learning methods are proposed. They are easy to use and outperform existing deterministic methods as well as PFE on challenging unconstrained scenarios. We also provide insightful analysis on how incorporating uncertainty estimation helps reducing the adverse effects of noisy samples and affects the feature learning.