DeepID3: Face Recognition with Very Deep Neural Networks

Abstract

The state-of-the-art of face recognition has been significantly advanced by the emergence of deep learning. Very deep neural networks recently achieved great success on general object recognition because of their superb learning capacity. This motivates us to investigate their effectiveness on face recognition. This paper proposes two very deep neural network architectures, referred to as DeepID3, for face recognition. These two architectures are rebuilt from stacked convolution and inception layers proposed in VGG net and GoogLeNet to make them suitable to face recognition. Joint face identification-verification supervisory signals are added to both intermediate and final feature extraction layers during training. An ensemble of the proposed two architectures achieves 99.53% LFW face verification accuracy and 96.0% LFW rank-1 face identification accuracy, respectively. A further discussion of LFW face verification result is given in the end.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Improving neural networks by preventing co-adaptation of feature detectors
• Learning Face Representation from Scratch
• Going Deeper with Convolutions
• Recover Canonical-View Faces in the Wild with Deep Neural Networks
• Surpassing Human-Level Face Verification Performance on LFW with GaussianFace
• Deeply learned face representations are sparse, selective, and robust
• Web-Scale Training for Face Identification

Cited by in corpus (42)

• Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments
• Enabling and Emerging Technologies for Social Distancing: A Comprehensive Survey and Open Problems
• MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
• Deep learning and face recognition: the state of the art
• Sampling Matters in Deep Embedding Learning
• NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• Attention-Aware Face Hallucination via Deep Reinforcement Learning
• AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
• WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
• Peak-Piloted Deep Network for Facial Expression Recognition
• Richer and Deeper Supervision Network for Salient Object Detection
• Decorrelated Adversarial Learning for Age-Invariant Face Recognition
• Improving Heterogeneous Face Recognition with Conditional Adversarial Networks
• Neural Architecture Search for Deep Face Recognition
• TAD: Trigger Approximation based Black-box Trojan Detection for AI
• Generative One-Shot Face Recognition
• Hierarchical Feature Embedding for Attribute Recognition
• Extended Labeled Faces in-the-Wild (ELFW): Augmenting Classes for Face Segmentation
• Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video
• Multi-Prototype Networks for Unconstrained Set-based Face Recognition
• Cassandra: Detecting Trojaned Networks from Adversarial Perturbations
• FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network
• Ptolemy: Architecture Support for Robust Deep Learning
• Inter-class Discrepancy Alignment for Face Recognition
• When 3D-Aided 2D Face Recognition Meets Deep Learning: An extended UR2D for Pose-Invariant Face Recognition
• Facial Feature Embedded CycleGAN for VIS-NIR Translation
• On Numerosity of Deep Neural Networks
• Person Identification with Visual Summary for a Safe Access to a Smart Home
• A Deep, Information-theoretic Framework for Robust Biometric Recognition
• Toward Building Safer Smart Homes for the People with Disabilities
• SafeNet: An Assistive Solution to Assess Incoming Threats for Premises
• Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier
• Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition
• A Novel Neural Network Model Specified for Representing Logical Relations
• AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements
• ClusterFace: Joint Clustering and Classification for Set-Based Face Recognition
• Remixing Music with Visual Conditioning
• Understanding Classifier Mistakes with Generative Models
• PipeTune: Pipeline Parallelism of Hyper and System Parameters Tuning for Deep Learning Clusters
• Privacy Preserving Recalibration under Domain Shift
• Large-scale Multi-modal Person Identification in Real Unconstrained Environments