Gaussian Mixture Distribution Makes Data Uncertainty Learning Better

As a mainstream method in face recognition, extracting separable facial features by deep CNNs in the latent space has achieved remarkable success. In most existing works, people often view the embedding features as points. Dealing with entirely unconstrained face images, DUL and PFE demonstrated that point estimation shows weak robusticity on the inherent noise in the input images (data uncertainty) and introduced the distribution estimation by modeling each latent feature using a Gaussian distribution. However, these two methods only apply a unimodal Gaussian prior distribution, which is insufficient to represent wild faces with complex variations. In this paper, we propose a novel face recognition framework based on the multivariate Gaussian mixture distribution (DUL-GM). Through numerous experiments, we show that compared with the prior works, the features modeled by multivariate Gaussian mixture distribution have a better interference suppression ability and achieve state-of-the-art performance on extensive challenging benchmarks.