Fast and Reliable Probabilistic Face Embeddings in the Wild

Abstract

Probabilistic Face Embeddings (PFE) can improve face recognition performance in unconstrained scenarios by integrating data uncertainty into the feature representation. However, existing PFE methods tend to be over-confident in estimating uncertainty and is too slow to apply to large-scale face matching. This paper proposes a regularized probabilistic face embedding method to improve the robustness and speed of PFE. Specifically, the mutual likelihood score (MLS) metric used in PFE is simplified to speedup the matching of face feature pairs. Then, an output-constraint loss is proposed to penalize the variance of the uncertainty output, which can regularize the output of the neural network. In addition, an identification preserving loss is proposed to improve the discriminative of the MLS metric, and a multi-layer feature fusion module is proposed to improve the neural network's uncertainty estimation ability. Comprehensive experiments show that the proposed method can achieve comparable or better results in 9 benchmarks than the state-of-the-art methods, and can improve the performance of risk-controlled face recognition. The code of our work is publicly available in GitHub (https://github.com/KaenChan/ProbFace).

arXiv comment17 pages

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• On Calibration of Modern Neural Networks
• Learning Face Representation from Scratch
• DeepID3: Face Recognition with Very Deep Neural Networks
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• RetinaFace: Single-stage Dense Face Localisation in the Wild
• Grad-CAM: Why did you say that?
• Word Representations via Gaussian Embedding
• Multicolumn Networks for Face Recognition
• Modeling Uncertainty with Hedged Instance Embedding
• Partial FC: Training 10 Million Identities on a Single Machine
• Inducing Predictive Uncertainty Estimation for Face Recognition
• On the Capacity of Face Representation
• Variational Inference to Measure Model Uncertainty in Deep Neural Networks
• Stochastic Prototype Embeddings

Cited by in corpus (2)

• Prototype Memory for Large-scale Face Representation Learning
• Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification