Deep Learning Face Representation by Joint Identification-Verification

2014/06/18 by Yi Sun, Xiaogang Wang, Sun, Yi +3 · 1 voice · 1,792 citations
Computer Science · Engineering · #Artificial intelligence #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Deep learning #Engineering #FOS: Computer and information sciences #Face (sociological concept) #Face and Expression Recognition #Face recognition and analysis #Facial recognition system #Feature (linguistics) #Feature extraction #Identification (biology) #Identity (music) #Key (lock) #Machine learning #Pattern recognition (psychology) #Representation (politics) #Task (project management) #Task analysis #cs.CV

paper · pdf · doi:10.48550/arxiv.1406.4773

published in arXiv (Cornell University) 27, 1988-1996 (Cornell University)

arxiv created 2014/06/18 · openalex publication_date 2014/06/18 · arxiv published 2014/06/18 · arxiv updated 2014/06/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

The key challenge of face recognition is to develop effective feature representations for reducing intra-personal variations while enlarging inter-personal differences. In this paper, we show that it can be well solved with deep learning and using both face identification and verification signals as supervision. The Deep IDentification-verification features (DeepID2) are learned with carefully designed deep convolutional networks. The face identification task increases the inter-personal variations by drawing DeepID2 extracted from different identities apart, while the face verification task reduces the intra-personal variations by pulling DeepID2 extracted from the same identity together, both of which are essential to face recognition. The learned DeepID2 features can be well generalized to new identities unseen in the training data. On the challenging LFW dataset, 99.15% face verification accuracy is achieved. Compared with the best deep learning result on LFW, the error rate has been significantly reduced by 67%.

Citations

• Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval
• Gradient-based learning applied to document recognition
• ImageNet classification with deep convolutional neural networks

Cited by

• A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition
• Tree Matching Networks for Natural Language Inference: Parameter-Efficient Semantic Understanding via Dependency Parse Trees
• Towards classification-based representation learning for place recognition on LiDAR scans
• PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymization
• Explaining Image Similarity with Automatically Extracted Concept Activation Vectors
• Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation
• MassFace: an efficient implementation using triplet loss for face recognition
• Deep Metric Learning with Density Adaptivity
• GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition
• "Who is Driving around Me?" Unique Vehicle Instance Classification using Deep Neural Features
• Face Synthesis for Eyeglass-Robust Face Recognition
• Object Recognition Datasets and Challenges: A Review
• FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box Queries
• ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks
• Face representation by deep learning: a linear encoding in a parameter space?
• Semantic Image Segmentation via Deep Parsing Network
• Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
• Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation
• Faceness-Net: Face Detection through Deep Facial Part Responses
• Adversarial Learning with Margin-based Triplet Embedding Regularization
• Implementation of Fruits Recognition Classifier using Convolutional Neural Network Algorithm for Observation of Accuracies for Various Hidden Layers
• A Discriminative Learned CNN Embedding for Remote Sensing Image Scene Classification
• Learning to Learn in a Semi-Supervised Fashion
• Discriminability Distillation in Group Representation Learning
• Dynamic Region-Aware Convolution
• Alpha-Net: Architecture, Models, and Applications
• Triplet Distillation for Deep Face Recognition
• Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
• Large-scale Bisample Learning on ID Versus Spot Face Recognition
• Striking the Right Balance with Uncertainty
• To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions
• Intelligent Frame Selection as a Privacy-Friendlier Alternative to Face Recognition
• Max-margin Class Imbalanced Learning with Gaussian Affinity
• On Learning Density Aware Embeddings
• Masked Face Recognition Challenge: The InsightFace Track Report
• DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• A survey of face recognition techniques under occlusion
• A Survey of Deep Facial Attribute Analysis
• Metric Classification Network in Actual Face Recognition Scene
• SphereFace2: Binary Classification is All You Need for Deep Face Recognition
• Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learning
• An Automatic System for Unconstrained Video-Based Face Recognition
• Image Super-Resolution Using Deep Convolutional Networks
• 3D Human Pose Estimation with Siamese Equivariant Embedding
• Learning Discriminative Features Via Weights-biased Softmax Loss
• Recent Advances in Deep Learning for Object Detection
• Robust Screening of COVID-19 from Chest X-ray via Discriminative Cost-Sensitive Learning
• MoDE: Mixture of Diffusion Experts for Any Occluded Face Recognition
• Improved Deep Hashing with Soft Pairwise Similarity for Multi-label Image Retrieval
• RobFR: Benchmarking Adversarial Robustness on Face Recognition
• Fundamental tenis : resep meraih kemenangan / Tony Mottram
• MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
• GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps
• Learning Deep Embeddings with Histogram Loss
• Look, Listen and Learn - A Multimodal LSTM for Speaker Identification
• Learning and Interpreting Gravitational-Wave Features from CNNs with a Random Forest Approach
• Deep Metric Learning with Spherical Embedding
• PAM: Pose Attention Module for Pose-Invariant Face Recognition
• Deep Networks with Fast Retraining
• Improved Super-Resolution Convolution Neural Network for Large Images
• MorphGuard: Morph Specific Margin Loss for Enhancing Robustness to Face Morphing Attacks
• Deep Metric Learning by Online Soft Mining and Class-Aware Attention
• Hierarchical Feature Embedding for Attribute Recognition
• Visual Diver Face Recognition for Underwater Human-Robot Interaction
• 3D Face Recognition: A Survey
• On Numerosity of Deep Neural Networks
• Learning to Cluster Faces via Confidence and Connectivity Estimation
• Balanced Alignment for Face Recognition: A Joint Learning Approach
• Joint Deep Cross-Domain Transfer Learning for Emotion Recognition
• The Multiverse Loss for Robust Transfer Learning
• On the Separability of Classes with the Cross-Entropy Loss Function
• Support Vector Guided Softmax Loss for Face Recognition
• Person Re-identification Attack on Wearable Sensing
• DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition
• Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images
• Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
• A Discriminatively Learned CNN Embedding for Person Reidentification
• Transductive Zero-Shot Hashing for Multilabel Image Retrieval
• GridFace: Face Rectification via Learning Local Homography Transformations
• Asymmetric Rejection Loss for Fairer Face Recognition
• Deep learning and face recognition: the state of the art
• Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples
• FingerNet: Pushing The Limits of Fingerprint Recognition Using Convolutional Neural Network
• Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification
• Decorrelated Adversarial Learning for Age-Invariant Face Recognition
• Environmental sound classification using convolution neural networks with different integrated loss functions
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition

Discussions

• Deep Learning Face Representation by Joint Identification-Verification [hn, 1 points, 0 comments]

Related

• DeepID3: Face Recognition with Very Deep Neural Networks
• DeepFace: Closing the Gap to Human-Level Performance in Face Verification
• Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
• Deeply learned face representations are sparse, selective, and robust
• 50 Years of Automated Face Recognition