鉴别器
分歧(语言学)
自编码
计算机科学
人工智能
理论(学习稳定性)
特征(语言学)
生成语法
模式识别(心理学)
钥匙(锁)
对抗制
Kullback-Leibler散度
图像(数学)
培训(气象学)
机器学习
人工神经网络
物理
哲学
探测器
气象学
电信
语言学
计算机安全
作者
Duhyeon Bang,Hyunjung Shim
出处
期刊:International Conference on Machine Learning
日期:2018-07-03
卷期号:: 433-442
被引量:19
摘要
Despite the success of generative adversarial networks (GANs) for image generation, the trade-off between visual quality and image diversity remains a significant issue. This paper achieves both aims simultaneously by improving the stability of training GANs. The key idea of the proposed approach is to implicitly regularize the discriminator using representative features. Focusing on the fact that standard GAN minimizes reverse Kullback-Leibler (KL) divergence, we transfer the representative feature, which is extracted from the data distribution using a pre-trained autoencoder (AE), to the discriminator of standard GANs. Because the AE learns to minimize forward KL divergence, our GAN training with representative features is influenced by both reverse and forward KL divergence. Consequently, the proposed approach is verified to improve visual quality and diversity of state of the art GANs using extensive evaluations.
科研通智能强力驱动
Strongly Powered by AbleSci AI