Deep Face Recognition: A Survey

TL;DR

This survey comprehensively reviews recent advances in deep face recognition, covering architectures, datasets, processing methods, and application scenarios, highlighting progress and future challenges in the field.

Contribution

It provides an organized overview of deep face recognition developments, including network designs, face processing techniques, and application contexts, with insights into technical challenges and future directions.

Findings

Summarizes various deep learning architectures and loss functions for face recognition.

Categorizes face processing methods into augmentation and normalization.

Reviews datasets and application scenarios in deep face recognition.

Abstract

Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction. This emerging technique has reshaped the research landscape of face recognition (FR) since 2014, launched by the breakthroughs of DeepFace and DeepID. Since then, deep learning technique, characterized by the hierarchical architecture to stitch together pixels into invariant face representation, has dramatically improved the state-of-the-art performance and fostered successful real-world applications. In this survey, we provide a comprehensive review of the recent developments on deep FR, covering broad topics on algorithm designs, databases, protocols, and application scenes. First, we summarize different network architectures and loss functions proposed in the rapid evolution of the deep FR methods. Second, the related face processing methods are categorized into two classes: "one-to-many augmentation" and "many-to-one normalization". Then, we summarize and compare the commonly used databases for both model training and evaluation. Third, we review miscellaneous scenes in deep FR, such as cross-factor, heterogenous, multiple-media and industrial scenes. Finally, the technical challenges and several promising directions are highlighted.