EPL: Empirical Prototype Learning for Deep Face Recognition

TL;DR

This paper introduces Empirical Prototype Learning (EPL), a novel method for deep face recognition that adaptively updates class prototypes based on sample similarity, improving robustness against hard samples and enhancing recognition accuracy.

Contribution

The paper proposes a new empirical prototype learning approach with adaptive margin parameters, explicitly defining prototypes as class feature expectations and updating them during training.

Findings

EPL improves face recognition accuracy across multiple datasets.

The adaptive margin strategy effectively handles hard samples.

Extensive experiments validate the superiority of EPL over existing methods.

Abstract

Prototype learning is widely used in face recognition, which takes the row vectors of coefficient matrix in the last linear layer of the feature extraction model as the prototypes for each class. When the prototypes are updated using the facial sample feature gradients in the model training, they are prone to being pulled away from the class center by the hard samples, resulting in decreased overall model performance. In this paper, we explicitly define prototypes as the expectations of sample features in each class and design the empirical prototypes using the existing samples in the dataset. We then devise a strategy to adaptively update these empirical prototypes during the model training based on the similarity between the sample features and the empirical prototypes. Furthermore, we propose an empirical prototype learning (EPL) method, which utilizes an adaptive margin parameter with respect to sample features. EPL assigns larger margins to the normal samples and smaller margins to the hard samples, allowing the learned empirical prototypes to better reflect the class center dominated by the normal samples and finally pull the hard samples towards the empirical prototypes through the learning. The extensive experiments on MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace demonstrate the effectiveness of EPL. Our code is available at $\href{https://github.com/WakingHours-GitHub/EPL}{https://github.com/WakingHours-GitHub/EPL}$.