Deep Learning Face Representation by Joint Identification-Verification

2014/06/18 by Yi Sun, Xiaogang Wang, Sun, Yi +3 · 14 citations
Computer Science · #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis

paper · pdf · doi:10.48550/arxiv.1406.4773

openalex publication_date 2014/06/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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
• ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks
• Face representation by deep learning: a linear encoding in a parameter space?

Related

• DeepID3: Face Recognition with Very Deep Neural Networks
• Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
• Deeply learned face representations are sparse, selective, and robust
• 50 Years of Automated Face Recognition
• Unconstrained Face Verification using Deep CNN Features