MIXED MEMBERSHIP GENERATIVE ADVERSARIAL NETWORKS

被引：0

作者：

Yazici, Yasin ^{[1
]}

Lecouat, Bruno ^{[1
]}

Yap, Kim Hui ^{[2
]}

Winkler, Stefan ^{[3
]}

Piliouras, Georgios ^{[4
]}

Chandrasekhar, Vijay ^{[1
]}

Foo, Chuan-Sheng ^{[1
]}

机构：

[1] Inst Infocomm Res I2R, Singapore, Singapore

[2] Nanyang Technol Univ, Singapore, Singapore

[3] Natl Univ Singapore, Singapore, Singapore

[4] Singapore Univ Technol & Design, Singapore, Singapore

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2022年

关键词：

generative models; generative adversarial networks; mixture models; mixture membership models;

D O I：

10.1109/ICIP46576.2022.9897640

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

GANs are designed to learn a single distribution, though multiple distributions can be modeled by treating them separately. However, this naive implementation does not consider overlapping distributions. We propose Mixed Membership Generative Adversarial Networks (MMGAN) analogous to mixed-membership models that model multiple distributions and discover their commonalities and particularities. Each data distribution is modeled as a mixture over a common set of generator distributions, and mixture weights are automatically learned from the data. Mixture weights can give insight into common and unique features of each data distribution. We evaluate our proposed MMGAN and show its effectiveness on MNIST and Fashion-MNIST with various settings.

引用

页码：1026 / 1030

页数：5

共 25 条

[1] Latent Dirichlet allocation [J].

Blei, DM ;

Ng, AY ;

Jordan, MI .

JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) :993-1022

[2]

Durugkar I., 2016, Generative multi-adversarial networks

[3]

Erosheva E., 2003, BAYESIAN STAT, V7

[4] Inference of population structure using multilocus genotype data: dominant markers and null alleles [J].

Falush, Daniel ;

Stephens, Matthew ;

Pritchard, Jonathan K. .

MOLECULAR ECOLOGY NOTES, 2007, 7 (04) :574-578

[5]

Fei-Fei L, 2005, PROC CVPR IEEE, P524

[6] Multi-Agent Diverse Generative Adversarial Networks [J].

Ghosh, Arnab ;

Kulharia, Viveka ;

Namboodiri, Vinay ;

Torr, Philip H. S. ;

Dokania, Puneet K. .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :8513-8521

[7] 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

[8]

Hoang Q., 2017, Multi-generator generative adversarial nets

[9]

Hoang Quan, 2018, P INT C LEARN REPR

[10]

Juefei-Xu F, 2017, ARXIV170404865

← 1 2 3 →