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 (3)

• 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

Cited by in corpus (12)

• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
• Deep learning and face recognition: the state of the art
• Defeating Image Obfuscation with Deep Learning
• 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
• A survey of face recognition techniques under occlusion
• SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet
• Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework
• DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification