由上海对外经贸大学人工智能与变革管理研究院与北京邮电大学、华东师范大学计算机科学与技术学院联合研发团队成员刘峰*、王晗阳（硕士研究生）、张嘉淏（本科生）、付子旺（硕士研究生）、周爱民*、齐佳音、李志斌合作撰写的学术论文“EvoGAN: An Evolutionary Computation Assisted GAN”被SCI检索期刊《Neurocomputing》（H-index=110，Impact=5.719）录用，该期刊是中科院SCI分区升级版的TOP期刊，主要发表人工神经网络、神经生物学、模糊逻辑学、脑与认知科学、机器学习、模式识别等领域的一流研究成果。
图像生成技术已被广泛应用于多个领域，近年，得益于生成对抗网络（Generative adversarial network, GAN）在理论与模型研究方面的发展，仅通过一张图像就能够实现对人类情感的识别与计算，生成以假乱真的面部表情。然而，当前的各类模型仍存在一定的局限性——它们只能生成具有基本表情的图像，或模仿一个表情，而不是生成复合表情。在现实生活中，人类的表情通常具有很大的多样性和复杂性。“EvoGAN: An Evolutionary Computation Assisted GAN”提出了一种进化算法（EA）辅助的对抗神经网络“EvoGAN”。EvoGAN使用EA在GAN学习的数据分布中搜索目标结果，可用于生成具有任何精确目标的复合表情图像，进一步，通过识别该合成图像的表情，实现了任意精确情绪的面部复合表达，即情绪面容输出。值得一提的是，EvoGAN是最早使用进化算法在生成对抗网络学习的数据分布中搜索目标结果的方法之一。
EvoGAN: An Evolutionary Computation Assisted GAN
Abstract:
The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings. However, all of these approaches uses gradients to condition the output, resulting in the outputting the same image with the same input. Also, they can only generate images with basic expression or mimic an expression instead of generating compound expression. In real life, however, human expressions are of great diversity and complexity. In this paper, we propose an evolutionary algorithm (EA) assisted GAN, named EvoGAN, to generate various compound expressions with any accurate target compound expression. EvoGAN uses an EA to search target results in the data distribution learned by GAN. Specifically, we use the Facial Action Coding System (FACS) as the encoding of an EA and use a pre-trained GAN to generate human facial images, and then use a pretrained classifier to recognize the expression composition of the synthesized images as the fitness function to guide the search of the EA. Combined random searching algorithm, various images with the target expression can be easily sythesized. Quantitative and Qualitative results are presented on several compound expressions, and the experimental results demonstrate the feasibility and the potential of EvoGAN. The source code is available at https://github.com/faceeyes/EvoGAN.
Keywords: Evolutionary algorithms; GAN; facial expression synthesis