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

arXiv: https://arxiv.org/abs/1501.04690 · HTML: https://mlsanity.com/paper/1501.04690/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2015.

## Built on by (most cited first, 10 of 10)

- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [Measuring Hidden Bias within Face Recognition via Racial Phenotypes](https://mlsanity.com/paper/2110.09839/) (2021)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [A Study on the Impact of Face Image Quality on Face Recognition in the Wild](https://mlsanity.com/paper/2307.02679/) (2023)
- [Impact of Facial Tattoos and Paintings on Face Recognition Systems](https://mlsanity.com/paper/2103.09939/) (2021)
- [StyleGAN as a Utility-Preserving Face De-identification Method](https://mlsanity.com/paper/2212.02611/) (2022)
- [Gender inference: can chatGPT outperform common commercial tools?](https://mlsanity.com/paper/2312.00805/) (2023)
- [Object Recognition Datasets and Challenges: A Review](https://mlsanity.com/paper/2507.22361/) (2025)
- [A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition](https://mlsanity.com/paper/2512.05928/) (2025)

## Abstract (arXiv)

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.