.png){kind=icon}
返回
Evolutionary Generative Adversarial Networks
.png){kind=icon}
OA
AI
DOI：10.1109/TEVC.2019.2895748.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Generative adversarial networks (GANs) have been effective for learning generative models for real-world data. However, accompanied with the generative tasks becoming more and more challenging, existing GANs (GAN and its variants) tend to suffer from different training problems such as instability and mode collapse. In this paper, we propose a novel GAN framework called evolutionary GANs (E-GANs) for stable GAN training and improved generative performance. Unlike existing GANs, which employ a predefined adversarial objective function alternately training a generator and a discriminator, we evolve a population of generators to play the adversarial game with the discriminator. Different adversarial training objectives are employed as mutation operations and each individual (i.e., generator candidature) are updated based on these mutations. Then, we devise an evaluation mechanism to measure the quality and diversity of generated samples, such that only well-performing generator(s) are preserved and used for further training. In this way, E-GAN overcomes the limitations of an individual adversarial training objective and always preserves the well-performing offspring, contributing to progress in, and the success of GANs. Experiments on several datasets demonstrate that E-GAN achieves convincing generative performance and reduces the training problems inherent in existing GANs.
Keyword:
Gallium nitride
Training
Generators
Generative adversarial networks
Evolutionary computation
Task analysis
Computational modeling
Deep generative models
evolutionary computation
generative adversarial networks (GANs)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
12
论文数:
1.8K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
Learning Common and Feature-Specific Patterns: A Novel Multiple-Sparse-Representation-Based Tracker
PREAI
分享收藏An Evolutionary Multiobjective Model and Instance Selection for Support Vector Machines With Pareto-Based Ensembles基于Pareto集成的支持向量机的进化多目标模型和实例选择
PREAI
分享收藏分享收藏
查看更多内容