{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:11:38Z","timestamp":1775578298117,"version":"3.50.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002611","name":"2020 Research Fund of the University of Seoul","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002611","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) by the Ministry of Science, ICT and Future Planning through the Basic Science Research Program","doi-asserted-by":"publisher","award":["2020R1F1A1075952"],"award-info":[{"award-number":["2020R1F1A1075952"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3270561","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T18:48:36Z","timestamp":1682534916000},"page":"43067-43079","source":"Crossref","is-referenced-by-count":4,"title":["Improving Complex Scene Generation by Enhancing Multi-Scale Representations of GAN Discriminators"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2967-7421","authenticated-orcid":false,"given":"Hanbit","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0063-0083","authenticated-orcid":false,"given":"Sang-Goo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7385-5494","authenticated-orcid":false,"given":"Jaehui","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Seoul, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4315-4117","authenticated-orcid":false,"given":"Junho","family":"Shim","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sookmyung Women’s University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref57","first-page":"12104","article-title":"Training generative adversarial networks with limited data","author":"karras","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref12","first-page":"1","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","first-page":"9378","article-title":"Data-efficient instance generation from instance discrimination","volume":"34","author":"yang","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","article-title":"Generating unseen complex scenes: Are we there yet?","author":"casanova","year":"2020","journal-title":"arXiv 2012 04027"},{"key":"ref59","first-page":"1","article-title":"DLID: Deep learning for domain adaptation by interpolating between domains","volume":"2","author":"chopra","year":"2013","journal-title":"Proc ICML Workshop Challenges Represent Learn"},{"key":"ref14","first-page":"3481","article-title":"Which training methods for GANs do actually converge?","author":"mescheder","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","first-page":"7559","article-title":"Differentiable augmentation for data-efficient GAN training","volume":"33","author":"zhao","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17317"},{"key":"ref11","article-title":"Geometric GAN","author":"hyun lim","year":"2017","journal-title":"arXiv 1705 02894"},{"key":"ref55","first-page":"1","article-title":"Training GANs with stronger augmentations via contrastive discriminator","author":"jeong","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","article-title":"Image augmentations for GAN training","author":"zhao","year":"2020","journal-title":"arXiv 2006 02595"},{"key":"ref17","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01369"},{"key":"ref19","first-page":"21271","article-title":"Bootstrap your own latent—A new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref51","first-page":"1","article-title":"Consistency regularization for generative adversarial networks","author":"zhang","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","first-page":"13019","article-title":"Self-supervised GANs with label augmentation","author":"hou","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01243"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01061"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref86","article-title":"Self-supervised learning with Swin Transformers","author":"xie","year":"2021","journal-title":"arXiv 2105 04553"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref85","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref88","first-page":"746","article-title":"Indoor segmentation and support inference from RGBD images","volume":"7576","author":"nathan silberman","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref49","first-page":"13253","article-title":"Self-supervised GAN: Analysis and improvement with multi-class minimax game","volume":"32","author":"tran","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00823"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref4","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv 1511 06434"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref5","first-page":"1","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"brock","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref82","article-title":"You only learn one representation: Unified network for multiple tasks","author":"wang","year":"2021","journal-title":"arXiv 2105 04206"},{"key":"ref81","first-page":"3927","article-title":"Improved precision and recall metric for assessing generative models","volume":"32","author":"kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref84","first-page":"1","article-title":"Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis","author":"liu","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref83","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref80","first-page":"1","article-title":"Demystifying MMD GANs","author":"bi?kowski","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref79","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"heusel","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"caron","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref78","article-title":"DepthFormer: Exploiting long-range correlation and local information for accurate monocular depth estimation","author":"li","year":"2022","journal-title":"arXiv 2203 14211"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref33","article-title":"Improved baselines with momentum contrastive learning","author":"chen","year":"2020","journal-title":"arXiv 2003 04297"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref76","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"yu","year":"2015","journal-title":"arXiv 1506 03365"},{"key":"ref2","first-page":"1","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00083"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00353"},{"key":"ref70","first-page":"27517","article-title":"Instance-conditioned GAN","volume":"34","author":"casanova","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01039"},{"key":"ref24","first-page":"1","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00935"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.02.003"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_14"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00666"},{"key":"ref69","article-title":"Freeze the discriminator: A simple baseline for fine-tuning GANs","author":"mo","year":"2020","journal-title":"arXiv 2002 10964"},{"key":"ref20","first-page":"1","article-title":"Projected GANs converge faster","author":"sauer","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00494"},{"key":"ref22","article-title":"Object detection in 20 years: A survey","author":"zou","year":"2019","journal-title":"arXiv 1905 05055"},{"key":"ref66","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume":"33","author":"zoph","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref29","article-title":"Patch-based image inpainting with generative adversarial networks","author":"demir","year":"2018","journal-title":"arXiv 1803 07422"},{"key":"ref60","first-page":"1","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00456"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_34"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10109094.pdf?arnumber=10109094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:46:56Z","timestamp":1685382416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10109094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3270561","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}