| 梯度策略的多目标GANs帕累托最优解算法 |
| |
| 引用本文： | 张波,徐黎明,黄志伟,要小鹏. 梯度策略的多目标GANs帕累托最优解算法[J]. 计算机工程与应用, 2021, 57(9): 89-95. DOI: 10.3778/j.issn.1002-8331.2004-0387 |
| |
| 作者姓名： | 张波 徐黎明 黄志伟 要小鹏 |
| |
| 作者单位： | 1.西南医科大学 医学信息与工程学院,四川 泸州 6460002.重庆邮电大学 计算机科学与技术学院,重庆 400065 |
| |
| 基金项目： | 四川省教育厅项目;四川省科技厅项目;国家自然科学基金 |
| |
| 摘 要： | 针对基于梯度策略的多目标优化算法无法适用于多目标、高维度的生成对抗网络(Generative Adversarial Nets,GANs)及多目标GANs中利用交叉验证产生次优解,极难求得最优解等问题,提出一种基于梯度策略的多目标GANs帕累托最优解算法.该算法采用硬参数共享方式,将多目标优化分解为多个两目标优化,确定...
|
| 关 键 词： | 梯度策略 多目标生成对抗网络 帕累托最优解 图像处理 |
Multi-objective GANs Pareto Optimality Algorithm Using Gradient Strategy |
| |
| ZHANG Bo,XU Liming,HUANG Zhiwei,YAO Xiaopeng. Multi-objective GANs Pareto Optimality Algorithm Using Gradient Strategy[J]. Computer Engineering and Applications, 2021, 57(9): 89-95. DOI: 10.3778/j.issn.1002-8331.2004-0387 |
| |
| Authors: | ZHANG Bo XU Liming HUANG Zhiwei YAO Xiaopeng |
| |
| Affiliation: | 1.School of Medical Information and Engineering, Southwest Medical University, Luzhou, Sichuan 646000, China2.School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China |
| |
| Abstract: | To address the problems that the gradient-based multi-objective algorithm cannot be applicable for multi-objective Generative Adversarial Nets（GANs） with high dimension and multiple tasks. Then, considering a fact that solutions with cross-of-validation can be sub-optimal and it is hard to search global solutions in optimizing multi-objective GANs, this paper presents a multi-objective GANs Pareto optimality algorithm based on gradient strategy. The proposed algorithm uses hardware parameter sharing method and decomposes multi-objective optimization into multiple binary-objective optimizations. Then, it computes and determines all the weighted parameters and searches Pareto optimality along the gradient direction, which can yield exactly Pareto optimality. Theoretically, it has been proved that the proposed method can result in one Pareto optimality with detailed demonstration. Practically, the proposed algorithm has been applied into common sub-fields of image processing to compare the source and proposed algorithm in the same setting. The experimental results show that the proposed algorithm has outperformed than source algorithms when the number of tasks is over 2. |
| |
| Keywords: | gradient strategy multi-objective generative adversarial nets Pareto optimality image processing |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
