Cross domain meta-network for sketch face recognition

Yuying Shao,Changwu Chen,Lin Cao,Kangning Du

doi:10.1051/matecconf/202133606007

Abstract

Because of the large modal difference between sketch image and optical image, and the problem that traditional deep learning methods are easy to overfit in the case of a small amount of training data, the Cross Domain Meta-Network for sketch face recognition method is proposed. This method first designs a meta-learning training strategy to solve the small sample problem, and then proposes entropy average loss and cross domain adaptive loss to reduce the modal difference between the sketch domain and the optical domain. The experimental results on UoM-SGFS and PRIP-VSGC sketch face data sets show that this method and other sketch face recognition methods.

Highlights

Sketch face recognition[1] is the process of matching face photos with sketch images
The traditional sketch face recognition methods can be roughly divided into three categories[3]: feature-based methods, the method based on synthesis and the method based on common subspace projection
The method based on subspace projection aims to project facial images of different modalities into a common subspace to reduce the influence of modal differences on recognition performance

Summary

Introduction

Sketch face recognition[1] is the process of matching face photos with sketch images. To solve the problem of modal differences, the algorithms currently designed for sketch face recognition can be divided into traditional sketch face recognition methods and deep learning-based methods. Feature-based methods aim to represent face images with local feature descriptors. This type of method usually results in the loss of details in the face image. The method based on subspace projection aims to project facial images of different modalities into a common subspace to reduce the influence of modal differences on recognition performance. This type of method may lose important information in the original image. The entropy mean loss and cross domain adaptive loss are proposed to reduce the modal difference between the sketch domain and the optical domain and improve the recognition ability of the model

Mean entropy loss

Cross domain adaptive loss

Implementation details

Comparative experiments

Conclusion