A generative adversarial network face recognition algorithm based on mean feature matching

The Generative Adversarial Network learns discriminative facial feature representations by training a generator network and a discriminator network to compete and cooperate with each other. This paper proposes a Generative Adversarial Network framework model based on mean feature matching. By mean feature matching losses, the Generator Network can learn feature representations that are closer to real faces, thereby improving the performance of face recognition. Through the analysis of experimental results, it is concluded that the Generative Adversarial Network framework model based on mean feature matching proposed in this paper has higher accuracy and stronger robust, and has achieved the most advanced results in various facial benchmark tests.