Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/95503
Title: | JDGAN : Enhancing generator on extremely limited data via joint distribution | Authors: | Li, W Xu, LC Liang, ZX Wang, SZ Cao, JN Lam, TC Cui, XH |
Issue Date: | 28-Mar-2021 | Source: | Neurocomputing, 28 Mar. 2021, v. 431, p. 148-162 | Abstract: | Generative Adversarial Network (GAN) is a thriving generative model and considerable efforts have been made to enhance the generation capabilities via designing a different adversarial framework of GAN (e.g., the discriminator and the generator) or redesigning the penalty function. Although existing models have been demonstrated to be very effective, their generation capabilities have limitations. Existing GAN variants either result in identical generated instances or generate simulation data with low quality when the training data are diverse and extremely limited (a dataset consists of a set of classes but each class holds several or even one single sample) or extremely imbalanced (a category holds a set of samples and other categories hold one single sample). In this paper, we present an innovative approach to tackle this issue, which jointly employs joint distribution and reparameterization method to reparameterize the randomized space as a mixture model and learn the parameters of this mixture model along with that of GAN. In this way, we term our approach Joint Distribution GAN (JDGAN). In our work, we show that the JDGAN can not only generate high quality simulation data with diversity, but also increase the overlapping area between the generating distribution and the raw data distribution. We proceed to conduct extensive experiments, utilizing MNIST, CIFAR10 and Mass Spectrometry datasets, all using extremely limited amounts of data, to demonstrate the significant performance of JDGAN in both achieving the smallest Fréchet Inception Distance (FID) score and producing diverse generated data. | Keywords: | Mode collapse Joint distribution Reparameterization GAN |
Publisher: | Elsevier | Journal: | Neurocomputing | ISSN: | 0925-2312 | EISSN: | 1872-8286 | DOI: | 10.1016/j.neucom.2020.12.001 | Rights: | © 2020 Elsevier B.V. All rights reserved © 2020. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/. The following publication Li, W., Xu, L., Liang, Z., Wang, S., Cao, J., Lam, T. C., & Cui, X. (2021). JDGAN: Enhancing generator on extremely limited data via joint distribution. Neurocomputing, 431, 148-162 is available at https://doi.org/10.1016/j.neucom.2020.12.001 |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Xu_Jdgan_Enhancing_Generator.pdf | Pre-Published version | 3.05 MB | Adobe PDF | View/Open |
Page views
94
Last Week
0
0
Last month
Citations as of Sep 22, 2024
Downloads
59
Citations as of Sep 22, 2024
SCOPUSTM
Citations
9
Citations as of Sep 26, 2024
WEB OF SCIENCETM
Citations
8
Citations as of Sep 26, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.