Progressive growing of GANs for improved quality, stability, and variation. Karras, T., Aila, T., Laine, S., & Lehtinen, J. 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings, 2018.
![Progressive growing of GANs for improved quality, stability, and variation [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CELEBA images at 10242. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CELEBA dataset.
@article{
title = {Progressive growing of GANs for improved quality, stability, and variation},
type = {article},
year = {2018},
pages = {1-26},
id = {2bace964-b3a2-3776-a3d4-335bc42f73d4},
created = {2022-09-21T09:29:20.054Z},
file_attached = {true},
profile_id = {ad172e55-c0e8-3aa4-8465-09fac4d5f5c8},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2022-09-21T09:29:45.681Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
folder_uuids = {b6d75013-efe2-4ddc-b3db-65496bd4db9f,103fae48-b63f-495b-9265-9049d2927097},
private_publication = {false},
abstract = {We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CELEBA images at 10242. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CELEBA dataset.},
bibtype = {article},
author = {Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko},
journal = {6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings}
}Downloads: 0
{"_id":"7oTL2WZHpGH4mfiqW","bibbaseid":"karras-aila-laine-lehtinen-progressivegrowingofgansforimprovedqualitystabilityandvariation-2018","authorIDs":[],"author_short":["Karras, T.","Aila, T.","Laine, S.","Lehtinen, J."],"bibdata":{"title":"Progressive growing of GANs for improved quality, stability, and variation","type":"article","year":"2018","pages":"1-26","id":"2bace964-b3a2-3776-a3d4-335bc42f73d4","created":"2022-09-21T09:29:20.054Z","file_attached":"true","profile_id":"ad172e55-c0e8-3aa4-8465-09fac4d5f5c8","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-09-21T09:29:45.681Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"b6d75013-efe2-4ddc-b3db-65496bd4db9f,103fae48-b63f-495b-9265-9049d2927097","private_publication":false,"abstract":"We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CELEBA images at 10242. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CELEBA dataset.","bibtype":"article","author":"Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko","journal":"6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings","bibtex":"@article{\n title = {Progressive growing of GANs for improved quality, stability, and variation},\n type = {article},\n year = {2018},\n pages = {1-26},\n id = {2bace964-b3a2-3776-a3d4-335bc42f73d4},\n created = {2022-09-21T09:29:20.054Z},\n file_attached = {true},\n profile_id = {ad172e55-c0e8-3aa4-8465-09fac4d5f5c8},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-09-21T09:29:45.681Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {b6d75013-efe2-4ddc-b3db-65496bd4db9f,103fae48-b63f-495b-9265-9049d2927097},\n private_publication = {false},\n abstract = {We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CELEBA images at 10242. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CELEBA dataset.},\n bibtype = {article},\n author = {Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko},\n journal = {6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings}\n}","author_short":["Karras, T.","Aila, T.","Laine, S.","Lehtinen, J."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/641e84f2-c958-a269-673a-7618159bf92a/171010196.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"karras-aila-laine-lehtinen-progressivegrowingofgansforimprovedqualitystabilityandvariation-2018","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","creationDate":"2021-03-03T03:31:06.487Z","downloads":0,"keywords":[],"search_terms":["progressive","growing","gans","improved","quality","stability","variation","karras","aila","laine","lehtinen"],"title":"Progressive growing of GANs for improved quality, stability, and variation","year":2018,"dataSources":["zeSfpfAFdsRF2mNyj","ya2CyA73rpZseyrZ8","aXmRAq63YsH7a3ufx","2252seNhipfTmjEBQ"]}