基于生成对抗网络的无监督域适应分类模型  

Unsupervised Domain Adaptation Classification Model Based on Generative Adversarial Network

作　　者：王格格 郭涛[1] 余游 苏菡[1] WANG Ge-ge;GUO Tao;YU You;SU Han(Department of Computer Science,Sichuan Normal University,Chengdu,Sichuan 610101,China)

机构地区：[1]四川师范大学计算机科学学院,四川成都610101

出　　处：《电子学报》2020年第6期1190-1197,共8页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61403266);四川省可视化与虚拟现实重点实验室项目(No.KJ201419)。

摘　　要：生成适应模型利用生成对抗网络实现模型结构,并在领域适应学习上取得了突破.但其部分网络结构缺少信息交互,且仅使用对抗学习不足以完全减小域间距离,从而使分类精度受到影响.为此,提出一种基于生成对抗网络的无监督域适应分类模型(Unsupervised Domain Adaptation classification model based on GAN,UDAG).该模型通过联合使用生成对抗网络和多核最大均值差异度量准则优化域间差异,并充分利用无监督对抗训练及监督分类训练之间的信息传递以学习源域分布和目标域分布之间的共享特征.通过在四种域适应情况下的实验结果表明,UDAG模型学习到更优的共享特征嵌入并实现了域适应图像分类,且分类精度有明显提高.Generate-to-adapt model has used generative adversarial network to implement model structure and has made a breakthrough in domain adaptation learning.However,some of its network structures lack information interaction,and the ability to use only adversarial learning is not sufficient to completely reduce the inter-domain distance.In this paper,an unsupervised domain adaptation classification model based on generative adversarial network(UDAG)is proposed.This model optimizes inter-domain differences and makes full use of the information between unsupervised confrontation training and supervised classification training to learn the shared features between the source and target domain distribution.The experimental results under four domain adaptation conditions show that the UDAG model learns better shared feature embedding and implements domain adaptive classification,and the classification accuracy is significantly improved.

关 键 词：生成适应模型 迁移学习 领域适应学习 生成对抗网络 多核最大均值差异 无监督学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]