MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
arXiv:1804.07573
Abstract
We present a class of extremely efficient CNN models, MobileFaceNets, which use less than 1 million parameters and are specifically tailored for high-accuracy real-time face verification on mobile and embedded devices. We first make a simple analysis on the weakness of common mobile networks for face verification. The weakness has been well overcome by our specifically designed MobileFaceNets. Under the same experimental conditions, our MobileFaceNets achieve significantly superior accuracy as well as more than 2 times actual speedup over MobileNetV2. After trained by ArcFace loss on the refined MS-Celeb-1M, our single MobileFaceNet of 4.0MB size achieves 99.55% accuracy on LFW and 92.59% TAR@FAR1e-6 on MegaFace, which is even comparable to state-of-the-art big CNN models of hundreds MB size. The fastest one of MobileFaceNets has an actual inference time of 18 milliseconds on a mobile phone. For face verification, MobileFaceNets achieve significantly improved efficiency over previous state-of-the-art mobile CNNs.
Accepted as a conference paper at CCBR 2018. Camera-ready version
References in corpus (10)
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- Learning Face Representation from Scratch
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- Xception: Deep Learning with Depthwise Separable Convolutions
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- A Light CNN for Deep Face Representation with Noisy Labels