# AirFace: Lightweight and Efficient Model for Face Recognition

arXiv: https://arxiv.org/abs/1907.12256 · HTML: https://mlsanity.com/paper/1907.12256/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [MixFaceNets: Extremely Efficient Face Recognition Networks](https://mlsanity.com/paper/2107.13046/) (2021)
- [QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization](https://mlsanity.com/paper/2206.10526/) (2022)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Information Maximization for Extreme Pose Face Recognition](https://mlsanity.com/paper/2209.03456/) (2022)
- [GROWN+UP: A Graph Representation Of a Webpage Network Utilizing Pre-training](https://mlsanity.com/paper/2208.02252/) (2022)
- [Efficient and Discriminative Image Feature Extraction for Universal Image Retrieval](https://mlsanity.com/paper/2409.13513/) (2024)
- [IDSelect: A RL-Based Cost-Aware Selection Agent for Video-based Multi-Modal Person Recognition](https://mlsanity.com/paper/2602.18990/) (2026)
- [Deep Boosting Multi-Modal Ensemble Face Recognition with Sample-Level Weighting](https://mlsanity.com/paper/2308.09234/) (2023)
- [Fully Quantized Always-on Face Detector Considering Mobile Image Sensors](https://mlsanity.com/paper/2311.01001/) (2023)

## Abstract (arXiv)

With the development of convolutional neural network, significant progress has been made in computer vision tasks. However, the commonly used loss function softmax loss and highly efficient network architecture for common visual tasks are not as effective for face recognition. In this paper, we propose a novel loss function named Li-ArcFace based on ArcFace. Li-ArcFace takes the value of the angle through linear function as the target logit rather than through cosine function, which has better convergence and performance on low dimensional embedding feature learning for face recognition. In terms of network architecture, we improved the the perfomance of MobileFaceNet by increasing the network depth, width and adding attention module. Besides, we found some useful training tricks for face recognition. With all the above results, we won the second place in the deepglint-light challenge of LFR2019.