自动化学报2018，Vol.44Issue(5)：819-828,10.DOI:10.16383/j.aas.2018.c170496
基于生成对抗网络的多视图学习与重构算法
Multi-view Learning and Reconstruction Algorithms via Generative Adversarial Networks
摘要
Abstract
Generally, objects often require to represent in different views. However, real-world applications in complex scenarios can hardly have complete views of a given object. In this paper, we propose generative adversarial network (GAN) based multi-view learning and reconstruction algorithms. A novel representation learning algorithm is proposed, which guarantees different views of the same object are mapped to the same representation. Meanwhile, the algorithm guarantees the representation carries enough reconstructed information. To construct multi-views of a given object, a generative adversarial network based reconstruction algorithm is proposed,which includes the representation information in the generation and discrimination models to guarantee the constructed views perfectly map the source view. The merits of the proposed algorithms lie in the fact that they avoid direct mapping among different views,and can solve the problem of missing views in training data and the problem of mapping between constructed views and the source views. Simulated experiments on handwritten digit dataset(MNIST),street view house numbers dataset(SVHN)and CelebFaces attributes dataset(CelebA)indicate that the proposed algorithms yield satisfactory reconstruction performances.关键词
多视图重构/条件生成对抗网络/多视图表征学习/生成模型Key words
Multi-view reconstruction/conditional generative adversarial networks(CGAN)/multi-view representation learning/generative models引用本文复制引用
孙亮,韩毓璇,康文婧,葛宏伟..基于生成对抗网络的多视图学习与重构算法[J].自动化学报,2018,44(5):819-828,10.基金项目
国家自然科学基金(61402076,61572104,61103146),吉林大学符号计算与知识工程教育部重点实验室项目(93K172017K03),中央高校基本科研业务项目(DUT17JC04)资助 Supported by National Natural Science Foundation of China(61402076,61572104,61103146),Project of Key Laboratory of Symbolic Computation and Knowledge Engineering of Jilin Uni-versity(93K172017K03),and Fundamental Research Funds for Central Universities(DUT17JC04) （61402076,61572104,61103146）
