A Semi-supervised Encoder Generative Adversarial Networks Model for Image Classification

被引：0

作者：

Fu, Xiao ^{[1
]}

Shen, Yuan-Tong ^{[1
]}

Li, Hong-Wei ^{[1
]}

Cheng, Xiao-Mei ^{[1
]}

机构：

[1] College of Mathematics and Physics, China University of Geosciences, Wuhan

来源：

Zidonghua Xuebao/Acta Automatica Sinica | 2020年 / 46卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Deep learning; Generative adversarial network (GAN); Image classification; Semi-supervised learning;

D O I：

10.16383/j.aas.c180212

中图分类号：

学科分类号：

摘要：

The semi-supervised image classification task has attracted more and more attention recently owing to the problem that adequate labeled data is hard to acquire from industrial applications. Meanwhile, considerable works demonstrate that the improved generative adversarial networks (GANs) can achieve great classification performance with only few labeled images. Intuitively, GAN is a generative model, there is no semantic feature extractor in the main framework. In order to further utilize the ability of GANs, we propose to add an encoder in the framework to extract features of images directly, and simultaneously to use a new semi-supervised training method to train this new image classification model. The classification results of experiments have shown the state-of-the-art accuracy performance in semi-supervised MNIST, SVHN and CIFAR-10. Copyright © 2020 Acta Automatica Sinica. All rights reserved.

引用

页码：531 / 539

页数：8

共 23 条

[1]

Zhang Hao-Kui, Li Ying, Jiang Ye-Nan, Deep learning for hyperspectral imagery classification: the state of the art and prospects, Acta Automatica Sinica, 44, 6, pp. 961-977, (2018)

[2]

Suddarth S C, Kergosien Y L., Rule-injection hints as a means of improving network performance and learning time, Neural Networks. EURASIP, 1990, pp. 120-129, (1990)

[3]

Li Min, Yu Long, Tian Sheng-Wei, Ibrahim T, Zhao Jian-Guo, Coreference resolution of uyghur noun phrases based on deep learning, Acta Automatica Sinica, 43, 11, pp. 1984-1992, (2017)

[4]

Wang Kun-Feng, Zuo Wang-Meng, Tan Ying, Qin Tao, Li Li, Wang Fei-Yue, Generative adversarial networks: from generating data to creating intelligence, Acta Automatica Sinica, 44, 5, pp. 769-774, (2018)

[5]

Dosovitskiy A, Fischer P, Springenberg J T, Riedmiller M, Brox T., Discriminative unsupervised feature learning with exemplar convolutional neural networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, 9, pp. 1734-1747, (2016)

[6]

Rasmus A, Valpola H, Honkala M, Berglund M, Raiko T., Semi-supervised learning with ladder networks, (2015)

[7]

Miyato T, Maeda S, Ishii S, Koyama M., Virtual adversarial training: a regularization method for supervised and semi-supervised learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, (2017)

[8]

Kingma D P, Rezende D J, Mohamed S, Welling M., Semi-supervised learning with deep generative models, Proceedings of the 2014 Neural Information Processing Systems, pp. 3581-3589, (2014)

[9]

Springenberg J T., Unsupervised and semi-supervised learning with categorical generative adversarial networks, (2015)

[10]

Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X., Improved techniques for training GANs, Proceedings of the 2016 Neural Information Processing Systems, pp. 1-10, (2016)

← 1 2 3 →