Single-Sample Face Recognition Based on Shared Generative Adversarial Network

doi:10.3390/math10050752

Single-Sample Face Recognition Based on Shared Generative Adversarial Network

2022-02-26

0

OA

AI

DOI：10.3390/math10050752

Original

Original request for help

Save

Abstract

En 中文

Single-sample face recognition is a very challenging problem, where each person has only one labeled training sample. It is difficult to describe unknown facial variations. In this paper, we propose a shared generative adversarial network (SharedGAN) to expand the gallery dataset. Benefiting from the shared decoding network, SharedGAN requires only a small number of training samples. After obtaining the generated samples, we join them into a large public dataset. Then, a deep convolutional neural network is trained on the new dataset. We use the well-trained model for feature extraction. With the deep convolutional features, a simple softmax classifier is trained. Our method has been evaluated on AR, CMU-PIE, and FERET datasets. Experimental results demonstrate the effectiveness of SharedGAN and show its robustness for single sample face recognition.

Single-Sample Face Recognition Based on Shared Generative Adversarial Network

Abstract

Journal

Organization

Cited Papers