On leveraging pretrained GANs for generation with limited data

M Zhao; Y Cong; L Carin

On leveraging pretrained GANs for generation with limited data

M Zhao, Y Cong, L Carin^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

46 Scopus citations

Abstract

Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting potential for augmenting …

Original language	English (US)
Journal	International Conference on …
State	Published - 2020
Externally published	Yes

Bibliographical note

Cited By (since 2020): 6

M1 - Query date: 2021-03-11 11:12:31

M1 - 6 cites: https://scholar.google.com/scholar?cites=16391058196447072580&as_sdt=2005&sciodt=0,5&hl=en

Access to Document

http://proceedings.mlr.press/v119/zhao20a.html

Cite this

@article{4aa9af77e14c49d5916dcda28d439cf9,

title = "On leveraging pretrained GANs for generation with limited data",

abstract = "Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting potential for augmenting …",

author = "M Zhao and Y Cong and L Carin",

note = "Cited By (since 2020): 6 M1 - Query date: 2021-03-11 11:12:31 M1 - 6 cites: https://scholar.google.com/scholar?cites=16391058196447072580&as_sdt=2005&sciodt=0,5&hl=en",

year = "2020",

language = "English (US)",

journal = "International Conference on …",

publisher = "proceedings.mlr.press",

}

TY - JOUR

T1 - On leveraging pretrained GANs for generation with limited data

AU - Zhao, M

AU - Cong, Y

AU - Carin, L

N1 - Cited By (since 2020): 6 M1 - Query date: 2021-03-11 11:12:31 M1 - 6 cites: https://scholar.google.com/scholar?cites=16391058196447072580&as_sdt=2005&sciodt=0,5&hl=en

PY - 2020

Y1 - 2020

N2 - Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting potential for augmenting …

AB - Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting potential for augmenting …

M3 - Article

JO - International Conference on …

JF - International Conference on …

ER -

On leveraging pretrained GANs for generation with limited data

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this