Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
This work addresses face recognition for security applications, but it is incremental as it builds on existing deep learning techniques and data accumulation.
The paper tackles the problem of face recognition performance by analyzing the impact of big data and presents a system achieving 99.50% accuracy on the LFW benchmark, outperforming previous state-of-the-art, while noting a gap between machine and human performance in real-world scenarios.
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.