自动化学报2018，Vol.44Issue(5)：804-810,7.DOI:10.16383/j.aas.2018.c170483
协作式生成对抗网络
Co-operative Generative Adversarial Nets
摘要
Abstract
Generative adversarial nets (GANs) combine the generative model with the discriminative model. With unsupervised training methods, the two types of models mutually improve through the adversarial process. It sets off a new machine learning boom in academia. The final goal of GANs learning is to fit any real-world data distribution. In practice,however,the real-world data distribution is difficult to estimate. The major problem is mode collapse,which may lead to redundancy and non-convergence. To improve the unsupervised generator and eliminate the risk of mode collapse, this paper proposes a novel co-operative network structure for GANs. Multiple generative models are constructed with a co-operative mechanism. It can help generative models to work together and learn from each other during training. In this way,the fitting ability of generators is largely enhanced,furthermore,the quality of generated data is eventually upgraded. Experiments are conducted on three different types of benchmark datasets. Results show that the new model significantly improves image generation,especially for human face pictures. Additionally,the co-operative mechanism can speed up the convergence,improve network's learning efficiency and deduct loss function noise. It also plays a certain role in 3D model generation and suppress the problem of mode collapse. In order to solve the inconsistency between generation model and discriminative model, a dynamic learning method is developed which can dynamically adjust learning frequency. It ultimately reduces unnecessary gradient penalties.关键词
生成对抗网络/协作式/模式坍塌/生成模型/无监督学习Key words
Generative adversarial nets(GANs)/co-operative/mode collapse/generative model/unsupervised learning Citation Zhang Long/Zhao Jie-Yu/Ye Xu-Lun/Dong Wei. Co-operative generative adversarial nets. Acta Automatica Sinica/2018/44(5): 804−810引用本文复制引用
张龙,赵杰煜,叶绪伦,董伟..协作式生成对抗网络[J].自动化学报,2018,44(5):804-810,7.基金项目
国家自然科学基金(61571247),浙江省自然科学基金(LZ16F030001),浙江省国际合作项目(2013C24027)资助 Supported by National Natural Science Foundation of China(61571247),National Natural Science Foundation of Zhe-jiang Province(LZ16F030001),and International Cooperation Projects of Zhejiang Province(2013C24027) （61571247）
