Semi-supervised Generative Adversarial Networks Based on Scalable Support Vector Machines and Manifold Regularization
作者单位:College of AutomationChongqing University of Posts and Telecommunications College of Computer Science and TechnologyChongqing University of Posts and Telecommunications College of Union with University of CincinnatiUniversity of Chongqing
会议名称:《第32届中国控制与决策会议》
会议日期:2020年
学科分类:12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
关 键 词:Generative adversarial networks semi-supervised learning Scalable SVM Manifold Regularization
摘 要:Generative adversarial networks(GANs) are potential models in semi-supervised learning because of the excellent performance of ***,most GAN-based semi-supervised models are sensitive to local perturbation,which means those models are not stable ***,Softmax classifier is the first choice of those *** this paper,a novel method is proposed by introducing a discriminator using scalable SVM classifier with manifold *** SVM classifiers typically perform better in small sample data sets compared with other classifiers,which is consistent with the feature that semi-supervised learning consists of a few labeled data and a large number of unlabeled *** regularization forces discriminator to keep invariable to local *** incorporating into feature-matching GAN architecture,the proposed GANs-based semi-supervised learning algorithm has advantages over other methods on the Cifar-10,SVHN and Cifar-100 *** results show that the proposed model SSVM-GAN has good robustness and strong generalization ability.