MMGAN: Manifold-Matching Generative Adversarial Networks

Noseong Park, Ankesh Anand, Joel Ruben Antony Moniz, Kookjin Lee, Jaegul Choo, David Keetae Park, Tanmoy Chakraborty, Hongkyu Park, Youngmin Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

It is well-known that GANs are difficult to train, and several different techniques have been proposed in order to stabilize their training. In this paper, we propose a novel training method called manifold-matching, and a new GAN model called manifold-matching GAN (MMGAN). MMGAN finds two manifolds representing the vector representations of real and fake images. If these two manifolds match, it means that real and fake images are statistically identical. To assist the manifold-matching task, we also use i) kernel tricks to find better manifold structures, ii) moving-averaged manifolds across mini-batches, and iii) a regularizer based on correlation matrix to suppress mode collapse. We conduct in-depth experiments with three image datasets and compare with several state-of-the-art GAN models. 32.4% of images generated by the proposed MMGAN are recognized as fake images during our user study (16% enhancement compared to other state-of-the-art model). MMGAN achieved an unsupervised inception score of 7.8 for CIFAR-10.

Original languageEnglish
Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1343-1348
Number of pages6
ISBN (Electronic)9781538637883
DOIs
Publication statusPublished - 2018 Nov 26
Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
Duration: 2018 Aug 202018 Aug 24

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2018-August
ISSN (Print)1051-4651

Conference

Conference24th International Conference on Pattern Recognition, ICPR 2018
CountryChina
CityBeijing
Period18/8/2018/8/24

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'MMGAN: Manifold-Matching Generative Adversarial Networks'. Together they form a unique fingerprint.

  • Cite this

    Park, N., Anand, A., Moniz, J. R. A., Lee, K., Choo, J., Park, D. K., Chakraborty, T., Park, H., & Kim, Y. (2018). MMGAN: Manifold-Matching Generative Adversarial Networks. In 2018 24th International Conference on Pattern Recognition, ICPR 2018 (pp. 1343-1348). [8545881] (Proceedings - International Conference on Pattern Recognition; Vol. 2018-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8545881