Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?

Abstract

Face recognition performance improves rapidly with the recent deep learning technique developing and underlying large training dataset accumulating. In this paper, we report our observations on how big data impacts the recognition performance. According to these observations, we build our Megvii Face Recognition System, which achieves 99.50% accuracy on the LFW benchmark, outperforming the previous state-of-the-art. Furthermore, we report the performance in a real-world security certification scenario. There still exists a clear gap between machine recognition and human performance. We summarize our experiments and present three challenges lying ahead in recent face recognition. And we indicate several possible solutions towards these challenges. We hope our work will stimulate the community's discussion of the difference between research benchmark and real-world applications.

References in corpus (4)

• 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
• HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition

Cited by in corpus (32)

• Deep Face Recognition: A Survey
• Robust Face Recognition via Multimodal Deep Face Representation
• Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
• Inferring Gender from Names on the Web: A Comparative Evaluation of Gender Detection Methods
• Recent Advances in Deep Learning Techniques for Face Recognition
• Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
• Deep learning and face recognition: the state of the art
• Face Recognition: From Traditional to Deep Learning Methods
• Defeating Image Obfuscation with Deep Learning
• Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• Range Loss for Deep Face Recognition with Long-tail
• Attention-Aware Face Hallucination via Deep Reinforcement Learning
• When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
• DeepGestalt - Identifying Rare Genetic Syndromes Using Deep Learning
• Measuring Hidden Bias within Face Recognition via Racial Phenotypes
• A survey of face recognition techniques under occlusion
• Generating Descriptions with Grounded and Co-Referenced People
• Deeper Interpretability of Deep Networks
• Person Recognition in Personal Photo Collections
• Impact of Facial Tattoos and Paintings on Face Recognition Systems
• SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet
• Large-scale Bisample Learning on ID Versus Spot Face Recognition
• Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
• Towards Interpretable Face Recognition
• StyleGAN as a Utility-Preserving Face De-identification Method
• Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework
• Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
• DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
• Attributes in Multiple Facial Images
• Sleep-deprived Fatigue Pattern Analysis using Large-Scale Selfies from Social Med