VIPLFaceNet: An Open Source Deep Face Recognition SDK

TL;DR

VIPLFaceNet is an open-source deep convolutional neural network for face recognition that achieves high accuracy and efficiency, significantly outperforming AlexNet on benchmark tests with a lightweight implementation.

Contribution

The paper introduces VIPLFaceNet, a novel deep face recognition network that is faster and more accurate than existing models, along with an open-source C++ SDK for practical use.

Findings

Achieves 98.60% accuracy on LFW with a single network.

Reduces training time by 80% and testing time by 40% compared to AlexNet.

Provides an efficient, open-source SDK suitable for real-world applications.

Abstract

Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a 10-layer deep convolutional neural network with 7 convolutional layers and 3 fully-connected layers. Compared with the well-known AlexNet, our VIPLFaceNet takes only 20% training time and 60% testing time, but achieves 40\% drop in error rate on the real-world face recognition benchmark LFW. Our VIPLFaceNet achieves 98.60% mean accuracy on LFW using one single network. An open-source C++ SDK based on VIPLFaceNet is released under BSD license. The SDK takes about 150ms to process one face image in a single thread on an i7 desktop CPU. VIPLFaceNet provides a state-of-the-art start point for both academic and industrial face recognition applications.