基于条件梯度Wasserstein生成对抗网络的图像识别 |
| |
引用本文: | 何子庆,聂红玉,刘月,尹洋.基于条件梯度Wasserstein生成对抗网络的图像识别[J].计算机测量与控制,2019,27(6):157-162. |
| |
作者姓名: | 何子庆 聂红玉 刘月 尹洋 |
| |
作者单位: | 西南交通大学,,, |
| |
基金项目: | 国家自然科学基金资助项目( 61461048);重庆市教委科学技术研究项目资助(KJQN201805702); 四川省科技创新苗子工程资助项目(2018102) |
| |
摘 要: | 生成式对抗网络GAN功能强大,但是具有收敛速度慢、训练不稳定、生成样本多样性不足等缺点。该文结合条件深度卷积对抗网络CDCGAN和带有梯度惩罚的Wasserstein生成对抗网络WGAN-GP的优点,提出了一个混合模型-条件梯度Wasserstein生成对抗网络CDCWGAN-GP,用带有梯度惩罚的Wasserstein距离训练对抗网络保证了训练稳定性且收敛速度更快,同时加入条件c来指导数据生成。另外为了增强判别器提取特征的能力,该文设计了全局判别器和局部判别器一起打分,最后提取判别器进行图像识别。实验结果证明,该方法有效的提高了图像识别的准确率。
|
关 键 词: | 生成式对抗网络 条件模型 Wesserstein 距离 梯度惩罚 全局和局部一致性 图像识别 |
收稿时间: | 2018/12/13 0:00:00 |
修稿时间: | 2019/1/10 0:00:00 |
Image Recognition With Conditional Wasserstein Generative Adversarial Networks with gradient penalty* |
| |
Abstract: | Generated adversarial net GAN is powerful,but it has some disadvantages such as slow convergence, unstable training, and insufficient sample diversity.This paper presents a conditional gradient Wasserstein generation confrontation network model CDCWGAN-GP by Combining the advantage of conditional deep convolution adversarial net CDCGAN and Wasserstein generated adversarial net with gradient penalty WGAN-GP. Using the Wasserstein distance training against the network with gradient penalty guarantees training stability and faster convergence, while adding condition c to guide data generation. In addition, in order to enhance the ability of the discriminator to extract features, the paper designs a global discriminator and a local discriminator to score together, and finally extracts the discriminator for image recognition. The result of simulation experiments show that this method effectively improves the accuracy of image recognition. |
| |
Keywords: | GAN conditional model Wesserstein distance gradient penalty global and local consistency image recognition |
|
| 点击此处可从《计算机测量与控制》浏览原始摘要信息 |
|
点击此处可从《计算机测量与控制》下载全文 |
|