DeepAI AI Chat
Log In Sign Up

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

by   Erjin Zhou, et al.
Megvii Technology Limited

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 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.


page 4

page 5


Masked Face Recognition Dataset and Application

In order to effectively prevent the spread of COVID-19 virus, almost eve...

Face Recognition: Perspectives from the Real-World

In this paper, we analyze some of our real-world deployment of face reco...

MegaFace: A Million Faces for Recognition at Scale

Recent face recognition experiments on the LFW benchmark show that face ...

Sparsifying Neural Network Connections for Face Recognition

This paper proposes to learn high-performance deep ConvNets with sparse ...

Deep Face Recognition: A Survey

Driven by graphics processing units (GPUs), massive amounts of annotated...

Two-Face: Adversarial Audit of Commercial Face Recognition Systems

Computer vision applications like automated face detection are used for ...

FaceX-Zoo: A PyTorch Toolbox for Face Recognition

Deep learning based face recognition has achieved significant progress i...