AirFace: Lightweight and Efficient Model for Face Recognition
This work addresses the need for lightweight and efficient models in face recognition, but it is incremental as it builds on existing methods like ArcFace and MobileFaceNet.
The paper tackled the problem of improving face recognition by proposing a novel loss function and enhancing network architecture, resulting in winning second place in the deepglint-light challenge of LFR2019.
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.