{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T05:25:33Z","timestamp":1743485133191,"version":"3.37.3"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100004344","name":"Adobe Systems Inc","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004344","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Graphics"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1016\/j.cag.2021.05.013","type":"journal-article","created":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T16:05:11Z","timestamp":1623341111000},"page":"188-196","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":19,"special_numbering":"C","title":["Neural architecture search for deep image prior"],"prefix":"10.1016","volume":"98","author":[{"given":"Kary","family":"Ho","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3898-0596","authenticated-orcid":false,"given":"Andrew","family":"Gilbert","sequence":"additional","affiliation":[]},{"given":"Hailin","family":"Jin","sequence":"additional","affiliation":[]},{"given":"John","family":"Collomosse","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.cag.2021.05.013_bib0001","series-title":"The IEEE conference on computer vision and pattern recognition (CVPR)","article-title":"Deep image prior","author":"Ulyanov","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0002","article-title":"Deep image prior","author":"Ulyanov","year":"2019","journal-title":"Intl J Comput Vis (IJCV)"},{"key":"10.1016\/j.cag.2021.05.013_bib0003","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/BF00113894","article-title":"Learning with genetic algorithms","volume":"3","author":"de Jong","year":"1988","journal-title":"J Mach Learn"},{"key":"10.1016\/j.cag.2021.05.013_bib0004","series-title":"Proc. ICLR","article-title":"Large-scale evolution of image classifiers","author":"Real","year":"2017"},{"key":"10.1016\/j.cag.2021.05.013_bib0005","series-title":"Proc. AAAI","article-title":"Aging evolution for image classifier architecture search","author":"Real","year":"2019"},{"key":"10.1016\/j.cag.2021.05.013_bib0006","series-title":"Proc. ECCV","article-title":"Progressive neural architecture search","author":"Liu","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0007","series-title":"Proc. ICLR","article-title":"Efficient multi-objective neural architecture search via lamarckian evolution","author":"Elsken","year":"2019"},{"key":"10.1016\/j.cag.2021.05.013_bib0008","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1007\/s11263-019-01170-8","article-title":"The devil is in the decoder: Classification, regression and GANs","volume":"127","author":"Wojna","year":"2019","journal-title":"Intl J Comput Vis (IJCV)"},{"key":"10.1016\/j.cag.2021.05.013_bib0009","series-title":"Proc. CVPR","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0010","first-page":"1","article-title":"Neural architecture search: a survey","volume":"20","author":"Elsken","year":"2019","journal-title":"J Mach Learn Res (JMLR)"},{"key":"10.1016\/j.cag.2021.05.013_bib0011","series-title":"Proc. CVPR","article-title":"Learning transferrable architectures for scalable image recognition","author":"Zoph","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0012","series-title":"Proc. NeurIPS","first-page":"8713","article-title":"Searching for efficient multi-scale architectures for dense image prediction","author":"Chen","year":"2018"},{"year":"2019","key":"10.1016\/j.cag.2021.05.013_sbref0013","article-title":"Automated machine learning: methods, systems, challenges"},{"key":"10.1016\/j.cag.2021.05.013_bib0014","series-title":"Proc. ICML","article-title":"Making a science of model search: hyper-parameter optimization in hundreds of dimensions for vision architectures","author":"Bergstra","year":"2013"},{"key":"10.1016\/j.cag.2021.05.013_bib0015","series-title":"Proc. IJCAI","article-title":"Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves","author":"Domhan","year":"2015"},{"key":"10.1016\/j.cag.2021.05.013_bib0016","series-title":"Proc. ICLR","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2017"},{"key":"10.1016\/j.cag.2021.05.013_bib0017","unstructured":"Schulman J., Wolski F., Dhariwal P., Radford A., Klimov O.. Proximal policy optimization algorithms. 2017. arXiv preprint arXiv:1707.06347."},{"key":"10.1016\/j.cag.2021.05.013_bib0018","series-title":"Proc. ICLR","article-title":"Designing neural network architectures using reinforcement learning","author":"Baker","year":"2017"},{"key":"10.1016\/j.cag.2021.05.013_bib0019","unstructured":"Negrinho R., Gordon G.. DeepArchitect: automatically designing and training deep architectures. 2017. arXiv preprint arXiv:1704.08792."},{"key":"10.1016\/j.cag.2021.05.013_bib0020","series-title":"Proc. ICCV","article-title":"AutoGAN: neural architecture search for generative adversarial networks","author":"Gong","year":"2019"},{"key":"10.1016\/j.cag.2021.05.013_bib0021","series-title":"Proc. AAAI","article-title":"Efficient architecture search by network transformation","author":"Cai","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0022","series-title":"Proc. Intl. Conf. on Genetic Algorithms","article-title":"Designing neural networks using genetic algorithms","author":"Miller","year":"1989"},{"issue":"1","key":"10.1016\/j.cag.2021.05.013_bib0023","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/72.265960","article-title":"An evolutionary algorithm that constructs recurrent neural networks","volume":"5","author":"Angeline","year":"1994","journal-title":"IEEE Trans Neural Netw"},{"key":"10.1016\/j.cag.2021.05.013_bib0024","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1162\/106365602320169811","article-title":"Evolving neural networks through augmenting topologies","volume":"10","author":"Stanley","year":"2002","journal-title":"Evol Comput"},{"key":"10.1016\/j.cag.2021.05.013_bib0025","unstructured":"Hu Y., Wu X., He R.. TF-NAS: rethinking three search freedoms of latency-constrained differentiable neural architecture search. arXiv preprint arXiv:2008053142020;."},{"key":"10.1016\/j.cag.2021.05.013_bib0026","series-title":"CVPR","article-title":"GreedyNAS: towards fast one-shot NAS with greedy supernet","author":"You","year":"2020"},{"key":"10.1016\/j.cag.2021.05.013_bib0027","series-title":"ICCV","article-title":"AutoDispNet: improving disparity estimation with automl","author":"Saikia","year":"2019"},{"key":"10.1016\/j.cag.2021.05.013_bib0028","series-title":"ICML","article-title":"Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search","author":"Suganuma","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0029","series-title":"ECCV","article-title":"NAS-DIP: learning deep image prior with neural architecture search","author":"Chen","year":"2020"},{"issue":"22","key":"10.1016\/j.cag.2021.05.013_bib0030","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1145\/882262.882264","article-title":"Graphcut textures: Image and video synthesis using graph cuts","volume":"3","author":"Kwatra","year":"2003","journal-title":"ACM Trans Graphics"},{"key":"10.1016\/j.cag.2021.05.013_bib0031","series-title":"Euro. Conf. on Comp. Vision (ECCV)","article-title":"Statistics of patch offsets for image completion","author":"He","year":"2012"},{"key":"10.1016\/j.cag.2021.05.013_bib0032","first-page":"1699","article-title":"Exemplar-based image inpainting using multiscale graph cuts","author":"Liu","year":"2013","journal-title":"IEEE Trans Image Process"},{"key":"10.1016\/j.cag.2021.05.013_bib0033","series-title":"Proc. Intl. Conf. on Computer Vision (ICCV)","article-title":"Texture Synthesis by non-parametric sampling","author":"Efros","year":"1999"},{"key":"10.1016\/j.cag.2021.05.013_bib0034","series-title":"ACM Transactions on Graphics (TOG)","article-title":"Scene completion using millions of photographs","author":"Hays","year":"2007"},{"key":"10.1016\/j.cag.2021.05.013_bib0035","series-title":"Proc. CVPR","article-title":"Disentangling structure and aesthetics for content-aware image completion","author":"Gilbert","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0036","series-title":"Proc. ACM SIGGRAPH","article-title":"PatchMatch: a randomized correspondence algorithm for structural image editing","author":"Barnes","year":"2009"},{"key":"10.1016\/j.cag.2021.05.013_bib0037","series-title":"Intl. conference on computer vision (ICCV)","article-title":"Super-resolution from a single image","author":"Glasner","year":"2009"},{"key":"10.1016\/j.cag.2021.05.013_bib0038","series-title":"Proc. ICCV","article-title":"Video inpainting: an internal learning approach","author":"Zhang","year":"2019"},{"key":"10.1016\/j.cag.2021.05.013_bib0039","series-title":"Proc. ICCV","article-title":"SinGAN: learning a generative model from a single natural image","author":"Shaham","year":"2019"},{"key":"10.1016\/j.cag.2021.05.013_bib0040","series-title":"Proc. CVPR","article-title":"Double-dip: unsupervised image decomposition via coupled deep-image-priors","author":"Gandelsman","year":"2018"},{"issue":"8","key":"10.1016\/j.cag.2021.05.013_bib0041","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","article-title":"StackGAN++: realistic image synthesis with stacked generative adversarial networks","volume":"41","author":"Zhang","year":"2017","journal-title":"IEEE Trans PAMI"},{"key":"10.1016\/j.cag.2021.05.013_bib0042","series-title":"Proc. CVPR 2018","article-title":"High-resolution image synthesis and semantic manipulation with conditional GANs","author":"Wang","year":"2018"},{"key":"10.1016\/j.cag.2021.05.013_bib0043","unstructured":"Yeh R., Chen C., Lim T.Y., Hasegawa-Johnson M., Do M.N.. Semantic image inpainting with perceptual and contextual losses. arXiv preprint arXiv:1607075392016;."},{"issue":"4","key":"10.1016\/j.cag.2021.05.013_bib0044","first-page":"107:1","article-title":"Globally and locally consistent image completion","volume":"36","author":"Iizuka","year":"2017","journal-title":"ACM Trans Graphics (Proc of SIGGRAPH 2017)"},{"key":"10.1016\/j.cag.2021.05.013_bib0045","unstructured":"Wilber M.J., Fang C., Jin H., Hertzmann A., Collomosse J., Belongie S.. Bam! the behance artistic media dataset for recognition beyond photography. arXiv preprint arXiv:1704086142017a;."},{"key":"10.1016\/j.cag.2021.05.013_bib0046","series-title":"Proc. NeurIPS","first-page":"2234","article-title":"Improved techniques for training GANs","author":"Salimans","year":"2016"},{"key":"10.1016\/j.cag.2021.05.013_bib0047","series-title":"Proc. NeurIPS","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local NASH equilibrium.","author":"Heusel","year":"2017"},{"key":"10.1016\/j.cag.2021.05.013_bib0048","unstructured":"Zhou B., Khosla A., Lapedriza A., Torralba A., Oliva A.. Places: an image database for deep scene understanding. arXiv preprint arXiv:1610020552016;."},{"key":"10.1016\/j.cag.2021.05.013_bib0049","series-title":"Proc. ICCV","article-title":"Bam! the behance artistic media dataset for recognition beyond photography","author":"Wilber","year":"2017"},{"key":"10.1016\/j.cag.2021.05.013_bib0050","series-title":"International conference on curves and surfaces","first-page":"711","article-title":"On single image scale-up using sparse-representations","author":"Zeyde","year":"2010"},{"issue":"4","key":"10.1016\/j.cag.2021.05.013_bib0051","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans Image Process"},{"key":"10.1016\/j.cag.2021.05.013_bib0052","series-title":"ACM TOG","article-title":"Image melding: combining inconsistent images using patch-based synthesis.","author":"Darabi","year":"2012"},{"key":"10.1016\/j.cag.2021.05.013_bib0053","series-title":"CVPR","article-title":"Context encoders: Feature learning by inpainting","author":"Pathak","year":"2016"}],"container-title":["Computers & Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849321001126?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849321001126?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T05:58:46Z","timestamp":1672811926000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0097849321001126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":53,"alternative-id":["S0097849321001126"],"URL":"https:\/\/doi.org\/10.1016\/j.cag.2021.05.013","relation":{},"ISSN":["0097-8493"],"issn-type":[{"type":"print","value":"0097-8493"}],"subject":[],"published":{"date-parts":[[2021,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Neural architecture search for deep image prior","name":"articletitle","label":"Article Title"},{"value":"Computers & Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cag.2021.05.013","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}