Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/95503
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Computing | en_US |
dc.contributor | School of Optometry | en_US |
dc.creator | Li, W | en_US |
dc.creator | Xu, LC | en_US |
dc.creator | Liang, ZX | en_US |
dc.creator | Wang, SZ | en_US |
dc.creator | Cao, JN | en_US |
dc.creator | Lam, TC | en_US |
dc.creator | Cui, XH | en_US |
dc.date.accessioned | 2022-09-20T06:35:33Z | - |
dc.date.available | 2022-09-20T06:35:33Z | - |
dc.identifier.issn | 0925-2312 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/95503 | - |
dc.language.iso | en | en_US |
dc.publisher | Elsevier | en_US |
dc.rights | © 2020 Elsevier B.V. All rights reserved | en_US |
dc.rights | © 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/. | en_US |
dc.rights | 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 | en_US |
dc.subject | Mode collapse | en_US |
dc.subject | Joint distribution | en_US |
dc.subject | Reparameterization | en_US |
dc.subject | GAN | en_US |
dc.title | JDGAN : Enhancing generator on extremely limited data via joint distribution | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 148 | en_US |
dc.identifier.epage | 162 | en_US |
dc.identifier.volume | 431 | en_US |
dc.identifier.doi | 10.1016/j.neucom.2020.12.001 | en_US |
dcterms.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. | en_US |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | Neurocomputing, 28 Mar. 2021, v. 431, p. 148-162 | en_US |
dcterms.isPartOf | Neurocomputing | en_US |
dcterms.issued | 2021-03-28 | - |
dc.identifier.isi | WOS:000618958800014 | - |
dc.identifier.scopus | 2-s2.0-85098962534 | - |
dc.identifier.eissn | 1872-8286 | en_US |
dc.description.validate | 202209 bcwh | en_US |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | COMP-0083 | - |
dc.description.fundingSource | RGC | en_US |
dc.description.fundingSource | Others | en_US |
dc.description.fundingText | National Key R&D Program of China | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 43997311 | - |
dc.description.oaCategory | Green (AAM) | en_US |
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
95
Last Week
0
0
Last month
Citations as of Oct 13, 2024
Downloads
68
Citations as of Oct 13, 2024
SCOPUSTM
Citations
9
Citations as of Oct 17, 2024
WEB OF SCIENCETM
Citations
8
Citations as of Oct 17, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.