MixFaceNets: Extremely Efficient Face Recognition Networks
arXiv:2107.13046
Abstract
In this paper, we present a set of extremely efficient and high throughput models for accurate face verification, MixFaceNets which are inspired by Mixed Depthwise Convolutional Kernels. Extensive experiment evaluations on Label Face in the Wild (LFW), Age-DB, MegaFace, and IARPA Janus Benchmarks IJB-B and IJB-C datasets have shown the effectiveness of our MixFaceNets for applications requiring extremely low computational complexity. Under the same level of computation complexity (< 500M FLOPs), our MixFaceNets outperform MobileFaceNets on all the evaluated datasets, achieving 99.60% accuracy on LFW, 97.05% accuracy on AgeDB-30, 93.60 TAR (at FAR1e-6) on MegaFace, 90.94 TAR (at FAR1e-4) on IJB-B and 93.08 TAR (at FAR1e-4) on IJB-C. With computational complexity between 500M and 1G FLOPs, our MixFaceNets achieved results comparable to the top-ranked models, while using significantly fewer FLOPs and less computation overhead, which proves the practical value of our proposed MixFaceNets. All training codes, pre-trained models, and training logs have been made available https://github.com/fdbtrs/mixfacenets.
arXiv commentAccepted at International Join Conference on Biometrics (IJCB 2021)
References in corpus (5)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- MixConv: Mixed Depthwise Convolutional Kernels
- ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
- Partial FC: Training 10 Million Identities on a Single Machine