Targeting Ultimate Accuracy: Face Recognition via Deep Embedding

Abstract

Face Recognition has been studied for many decades. As opposed to traditional hand-crafted features such as LBP and HOG, much more sophisticated features can be learned automatically by deep learning methods in a data-driven way. In this paper, we propose a two-stage approach that combines a multi-patch deep CNN and deep metric learning, which extracts low dimensional but very discriminative features for face verification and recognition. Experiments show that this method outperforms other state-of-the-art methods on LFW dataset, achieving 99.77% pair-wise verification accuracy and significantly better accuracy under other two more practical protocols. This paper also discusses the importance of data size and the number of patches, showing a clear path to practical high-performance face recognition systems in real world.

References in corpus (5)

• Deep Learning Face Representation by Joint Identification-Verification
• Learning Face Representation from Scratch
• DeepID3: Face Recognition with Very Deep Neural Networks
• Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
• Deeply learned face representations are sparse, selective, and robust

Cited by in corpus (36)

• Deep Face Recognition: A Survey
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• CosFace: Large Margin Cosine Loss for Deep Face Recognition
• A Light CNN for Deep Face Representation with Noisy Labels
• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
• Recent Advances in Deep Learning Techniques for Face Recognition
• Efficient Facial Representations for Age, Gender and Identity Recognition in Organizing Photo Albums using Multi-output CNN
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• Range Loss for Deep Face Recognition with Long-tail
• Minimum Margin Loss for Deep Face Recognition
• Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
• Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network
• DeepGestalt - Identifying Rare Genetic Syndromes Using Deep Learning
• Maximum A Posteriori Estimation of Distances Between Deep Features in Still-to-Video Face Recognition
• Striking the Right Balance with Uncertainty
• Deep Imbalanced Learning for Face Recognition and Attribute Prediction
• Max-margin Class Imbalanced Learning with Gaussian Affinity
• Deep Evidential Regression
• Stochastic Prototype Embeddings
• Git Loss for Deep Face Recognition
• Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)
• Neural Architecture Search for Deep Face Recognition
• Domain Balancing: Face Recognition on Long-Tailed Domains
• Ring loss: Convex Feature Normalization for Face Recognition
• Frankenstein: Learning Deep Face Representations using Small Data
• Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
• AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond
• Measurement-driven Security Analysis of Imperceptible Impersonation Attacks
• Feature Level Fusion from Facial Attributes for Face Recognition
• Unifying Identification and Context Learning for Person Recognition
• Inferring User Gender from User Generated Visual Content on a Deep Semantic Space
• DAIL: Dataset-Aware and Invariant Learning for Face Recognition
• AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements
• Object Specific Deep Learning Feature and Its Application to Face Detection
• Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition