Data Uncertainty Learning in Face Recognition

Abstract

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.

arXiv commentAccepted as poster by CVPR2020

References in corpus (11)

• Auto-Encoding Variational Bayes
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Squeeze-and-Excitation Networks
• Learning Face Representation from Scratch
• Weight Uncertainty in Neural Networks
• Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
• L2-constrained Softmax Loss for Discriminative Face Verification
• Multicolumn Networks for Face Recognition
• On the Capacity of Face Representation
• Towards Interpretable Face Recognition

Cited by in corpus (4)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Prototype Memory for Large-scale Face Representation Learning
• RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection
• Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval