Deep Face Recognition: A Survey

By Mei Wang, Weihong Deng. Neurocomputing, 2018

1,446 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/21117380118ddce47b3c515c5228372c513e61ba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network (2018, background): “The emergence of deep convolutional neural networks (CNN) [38, 55, 59, 31, 32] greatly advances the frontier of face recognition (FR) [63, 58, 54].”
Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition (2020, methodology): “Many studies [7, 20, 43, 44, 48, 58] point out that a noisy dataset is very harmful to model training.”
Epileptic Seizures Detection Using Deep Learning Techniques: A Review (2020, background): “2D - CONVOLUTIONAL NEURAL NETWORKS Nowadays, deep 2D networks are applied to resolve a wide range of computer vision obstacles such as image segmentation [28], medical image classification [29], and face recognition [30].”
Fine-Grained Image Analysis With Deep Learning: A Survey (2021, background): “3), for more information, we refer readers to survey papers of these spe-ciﬁc topics, e.g., [7], [34], [40].”
Generative Adversarial Networks for Face Generation: A Survey (2022, background): “They focus on network evolution from traditional to deep learning based CNNs [51, 99].”
The Creation and Detection of Deepfakes (2020, background): “Deep convolutions neural networks are very good at face recognition, achieving state-of-the-art performance [92, 116].”
Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data (2019, background): “Deep convolutional neuron networks (DCNNs) have achieved great success in computer vision [11,12,18,19,29], signiﬁcantly improving the state of art in face recognition [6, 7, 21, 28, 36, 37, 39].”
SSD: A Unified Framework for Self-Supervised Outlier Detection (2021, background): “Deep neural networks are at the cornerstone of multiple safety-critical applications, ranging from autonomous driving [39] to biometric authentication [32, 16].”
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models (2021, background): “Content-based Image Retrieval (CBIR) refers to the use of image-only queries for product search [26], face recognition [29, 34], etc.”
A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2021, background): “Note that face detection, face identification, and face reconstruction are subtasks of face recognition [50].”
Advances in adversarial attacks and defenses in computer vision: A survey (2021, background): “With highly active deep learning-based vision research for autonomous vehicles [17], face recognition [18], [19], robotics [20] and surveillance systems [21] etc.”
HeadNeRF: A Realtime NeRF-based Parametric Head Model (2021, background): “The parametric face/head model, which encodes the human face/head in low-dimensional space, is a hot research topic in computer vision and computer graphics and widely used in many applications like identity recognition [34, 52], face analysis [11, 64] and film/game production [47], etc.”