BEGAN: Boundary Equilibrium Generative Adversarial Networks. Berthelot, D., Schumm, T., & Metz, L. arXiv:1703.10717 [cs, stat], May, 2017. arXiv: 1703.10717![BEGAN: Boundary Equilibrium Generative Adversarial Networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.
@article{berthelot_began_2017,
title = {{BEGAN}: {Boundary} {Equilibrium} {Generative} {Adversarial} {Networks}},
shorttitle = {{BEGAN}},
url = {http://arxiv.org/abs/1703.10717},
abstract = {We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.},
language = {en},
urldate = {2022-01-19},
journal = {arXiv:1703.10717 [cs, stat]},
author = {Berthelot, David and Schumm, Thomas and Metz, Luke},
month = may,
year = {2017},
note = {arXiv: 1703.10717},
keywords = {/unread, Computer Science - Machine Learning, Statistics - Machine Learning, ⛔ No DOI found},
}
Downloads: 0
{"_id":"n7MC2P67LKidzxoPe","bibbaseid":"berthelot-schumm-metz-beganboundaryequilibriumgenerativeadversarialnetworks-2017","downloads":0,"creationDate":"2018-08-20T17:47:15.752Z","title":"BEGAN: Boundary Equilibrium Generative Adversarial Networks","author_short":["Berthelot, D.","Schumm, T.","Metz, L."],"year":2017,"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","bibdata":{"bibtype":"article","type":"article","title":"BEGAN: Boundary Equilibrium Generative Adversarial Networks","shorttitle":"BEGAN","url":"http://arxiv.org/abs/1703.10717","abstract":"We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.","language":"en","urldate":"2022-01-19","journal":"arXiv:1703.10717 [cs, stat]","author":[{"propositions":[],"lastnames":["Berthelot"],"firstnames":["David"],"suffixes":[]},{"propositions":[],"lastnames":["Schumm"],"firstnames":["Thomas"],"suffixes":[]},{"propositions":[],"lastnames":["Metz"],"firstnames":["Luke"],"suffixes":[]}],"month":"May","year":"2017","note":"arXiv: 1703.10717","keywords":"/unread, Computer Science - Machine Learning, Statistics - Machine Learning, ⛔ No DOI found","bibtex":"@article{berthelot_began_2017,\n\ttitle = {{BEGAN}: {Boundary} {Equilibrium} {Generative} {Adversarial} {Networks}},\n\tshorttitle = {{BEGAN}},\n\turl = {http://arxiv.org/abs/1703.10717},\n\tabstract = {We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.},\n\tlanguage = {en},\n\turldate = {2022-01-19},\n\tjournal = {arXiv:1703.10717 [cs, stat]},\n\tauthor = {Berthelot, David and Schumm, Thomas and Metz, Luke},\n\tmonth = may,\n\tyear = {2017},\n\tnote = {arXiv: 1703.10717},\n\tkeywords = {/unread, Computer Science - Machine Learning, Statistics - Machine Learning, ⛔ No DOI found},\n}\n\n","author_short":["Berthelot, D.","Schumm, T.","Metz, L."],"key":"berthelot_began_2017","id":"berthelot_began_2017","bibbaseid":"berthelot-schumm-metz-beganboundaryequilibriumgenerativeadversarialnetworks-2017","role":"author","urls":{"Paper":"http://arxiv.org/abs/1703.10717"},"keyword":["/unread","Computer Science - Machine Learning","Statistics - Machine Learning","⛔ No DOI found"],"metadata":{"authorlinks":{}},"html":""},"search_terms":["began","boundary","equilibrium","generative","adversarial","networks","berthelot","schumm","metz"],"keywords":["/unread","computer science - machine learning","statistics - machine learning","⛔ no doi found"],"authorIDs":[],"dataSources":["NyBbkYhtYKHg8fY2r","CmHEoydhafhbkXXt5"]}