计算机科学
生成语法
人工智能
生成对抗网络
图像(数学)
模式识别(心理学)
对抗制
生成模型
鉴别器
图像翻译
发电机(电路理论)
机器学习
作者
Ming Li,Rui Xi,Mengshu Hou
出处
期刊:International Joint Conference on Neural Network
日期:2018-07-01
标识
DOI:10.1109/ijcnn.2018.8489080
摘要
In recent years, Generative Adversarial Networks (GANs) have achieved significant improvements in image processing, especially image-to-image translation problem and image generation. But, few works are presented to creatively produce a novel domain from many training datasets with different domains. Inspired by creating a new calligraphic style, we propose a novel GAN model that supports creatively generate data domain, such as context, style and so on. In this paper, we call it as WHGAN. What is one key innovation is that WHGAN brings in a discriminative set (contains k discriminative models) that each one is responsible for a training dataset, in addition, the single generative model obtains feedbacks from discriminative models and produces a novel data distribution. Relatively, each discriminative model distinguishes the generated data distribution from its corresponding input dataset. Meanwhile, in order to make the generated data adjustable, we redesign the objective function with a set of variable weights that each one is responsible for a discriminator. For ease of presentation, we set k to be 2 in our implementation. Then, we conduct two evaluation on image dataset and synthesized 2D dataset respectively. Results show that WHGAN successfully generates oil-painting style images from photo-realistic and cartoon style inputs, furthermore, we also visually and objectively verify the impact of weights.
科研通智能强力驱动
Strongly Powered by AbleSci AI