| 基于互信息约束的生成对抗网络分类模型 |
| |
| 作者姓名： | 胡兵兵 唐华 吴幼龙 |
| |
| 作者单位： | 1. 上海科技大学信息科学与技术学院, 上海 201210;2. 中国科学院上海微系统与信息技术研究所, 上海 200050;3. 中国科学 院大学, 北京 100049 |
| |
| 基金项目： | 国家自然科学基金(61901267)和上海市浦江人才计划(18PJ1408500)资助 |
| |
| 摘 要： | 传统的机器学习方法需要大量的含标注数据集来训练模型,并且容易引发过拟合,而生成对抗网络可以无监督地进行训练。此外,互信息约束能够让模型生成指定类别的数据,可用于扩充数据集。提出InfoCatGAN和C-InfoGAN两种模型,前者在CatGAN的基础上增加了互信息约束,使得生成的图片更加逼真;后者使用InfoGAN模型中的辅助网络Q做分类,能够在生成高质量图片的同时,达到较好的分类准确率。二者均能通过隐变量控制生成图片的类别,这对数据增强具有一定意义。另外,在加入少量标签信息之后,模型的准确率能有所提升。
|
| 关 键 词： | 生成对抗网络 无监督学习 半监督学习 互信息 |
| 收稿时间： | 2020-04-27 |
| 修稿时间： | 2020-08-10 |
Classification models based on generative adversarial networks with mutual information regularization |
| |
| Authors: | HU Bingbing TANG Hua WU Youlong |
| |
| Institution: | 1. School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China;2. Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Science, Shanghai 200050, China;3. University of Chinese Academy of Science, Beijing 100049, China |
| |
| Abstract: | This paper studies classification models based on generative adversarial networks with mutual information regularization. Traditional machine learning methods rely on a large number of labeled datasets, which are scarce in practice, to train the model and can easily overfit to spurious correlations in the data; while generating adversarial networks can be trained in an unsupervised manner. In addition, mutual information constraint allows the model to generate data of a specified through latent variables, which has a certain significance for data augmentation. Moreover, after adding a small amount of label information, the accuracy of the model can be improved. category, which can be used to expand the data set. This paper proposes the InfoCatGAN and CInfoGAN classification models. The former adds the mutual information term to CatGAN model in order to generate images of higher visual fidelity; the latter uses the InfoGAN model for classification, which can ensure the quality of the generated images and provide a mentionable classification accuracy. Additionally, both two models can control the category of generated images |
| |
| Keywords: | GANs unsupervised learning semi-supervised learning mutual information |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
|
