Semi-Supervised Learning using Adversarial Networks

被引:0
作者
Tachibana, Ryosuke [1 ]
Matsubara, Takashi [1 ]
Uehara, Kuniaki [1 ]
机构
[1] Kobe Univ, Grad Sch Syst Informat, Kobe, Hyogo, Japan
来源
2016 IEEE/ACIS 15TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE (ICIS) | 2016年
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Semi-supervised learning is a topic of practical importance because of the difficulty of obtaining numerous labeled data. In this paper, we apply an extension of adversarial autoencoder to semi-supervised learning tasks. In attempt to separate style and content, we divide the latent representation of the autoencoder into two parts. We regularize the autoencoder by imposing a prior distribution on both parts to make them independent. As a result, one of the latent representations is associated with content, which is useful to classify the images. We demonstrate that our method disentangles style and content of the input images and achieves less test error rate than vanilla autoencoder on MNIST semi-supervised classification tasks.
引用
收藏
页码:939 / 944
页数:6
相关论文
共 17 条
[1]  
[Anonymous], 2015, ABS151105644 CORR
[2]  
[Anonymous], 2014, ADAM METHOD STOCHAST
[3]  
Burges Christopher J.C., 2013, THE MNIST DATABASE
[4]  
Chapelle Olivier., 2006, A semi-supervised learning, V1
[5]   Generative Adversarial Networks [J].
Goodfellow, Ian ;
Pouget-Abadie, Jean ;
Mirza, Mehdi ;
Xu, Bing ;
Warde-Farley, David ;
Ozair, Sherjil ;
Courville, Aaron ;
Bengio, Yoshua .
COMMUNICATIONS OF THE ACM, 2020, 63 (11) :139-144
[6]   Reducing the dimensionality of data with neural networks [J].
Hinton, G. E. ;
Salakhutdinov, R. R. .
SCIENCE, 2006, 313 (5786) :504-507
[7]  
Hinton G. E., 2012, ABS12070580 CORR
[8]  
Ioffe S., 2015, J MACHINE LEARNING R, V37
[9]  
Kingma D., 2014, ARXIV13126114
[10]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90