{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T02:54:45Z","timestamp":1769914485057,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012709","name":"National Council of Humanities, Science, and Technology (CONAHCyT) through Ciencia de Frontera 2023","doi-asserted-by":"publisher","award":["CF-2023-I-801"],"award-info":[{"award-number":["CF-2023-I-801"]}],"id":[{"id":"10.13039\/501100012709","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CONAHCyT through Scholarship","award":["829049"],"award-info":[{"award-number":["829049"]}]},{"name":"Azure Sponsorship Credits granted by Microsoft\u2019s AI for Good Research Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3581919","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T17:29:19Z","timestamp":1750440559000},"page":"107187-107203","source":"Crossref","is-referenced-by-count":2,"title":["Beyond Performance: Designing a Super-Resolution Architecture Search Space and a Hybrid Multi-Objective Approach for Neural Architecture Optimization"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8561-9886","authenticated-orcid":false,"given":"Jes\u00fas Leopoldo Llano","family":"Garc\u00eda","sequence":"first","affiliation":[{"name":"School of Engineering and Sciences, Tecnológico de Monterrey, Ciudad López Mateos, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3465-995X","authenticated-orcid":false,"given":"Ra\u00fal","family":"Monroy","sequence":"additional","affiliation":[{"name":"School of Engineering and Sciences, Tecnológico de Monterrey, Ciudad López Mateos, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1099-8148","authenticated-orcid":false,"given":"V\u00edctor Adri\u00e1n Sosa","family":"Hern\u00e1ndez","sequence":"additional","affiliation":[{"name":"School of Engineering and Sciences, Tecnológico de Monterrey, Ciudad López Mateos, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7402-9939","authenticated-orcid":false,"given":"Kalyanmoy","family":"Deb","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2982166"},{"key":"ref2","first-page":"1","article-title":"Efficient multi-objective neural architecture search via Lamarckian evolution","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Elsken"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3067574"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1905.01392"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103495"},{"key":"ref6","first-page":"17129","article-title":"CLEARER: Multi-scale neural architecture search for image restoration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Gou"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-3995.1999.tb00173.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73297-6_1"},{"key":"ref9","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"Petroski Such","year":"2017","journal-title":"arXiv:1712.06567"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075039"},{"key":"ref11","article-title":"M-FasterSeg: An efficient semantic segmentation network based on neural architecture search","author":"Kuang","year":"2021","journal-title":"CoRR"},{"key":"ref12","first-page":"4771","article-title":"Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Suganuma"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852417"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06849-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-017-9351-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-32494-1_8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3371432"},{"key":"ref21","article-title":"Genetic programming and gradient descent: A memetic approach to binary image classification","author":"Patrick Evans","year":"2019","journal-title":"arXiv:1909.13030"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10928-8_15"},{"key":"ref23","article-title":"Zero-cost proxies for lightweight NAS","author":"Abdelfattah","year":"2021","journal-title":"arXiv:2101.08134"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-54605-1_40"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395423"},{"key":"ref26","article-title":"Efficient residual dense block search for image super-resolution","author":"Song","year":"2019","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_26"},{"key":"ref28","article-title":"Multi-objective reinforced evolution in mobile neural architecture search","author":"Chu","year":"2019","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413080"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3003517"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3230824"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/a11100144"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00976-w"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102633"},{"key":"ref35","article-title":"Deep neural networks with multi-branch architectures are less non-convex","author":"Zhang","year":"2018","journal-title":"arXiv:1806.01845"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/math12172736"},{"key":"ref37","first-page":"1","article-title":"Efficient super-resolution transformer (ESRT)","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshops","volume":"2022","author":"Lu"},{"key":"ref38","first-page":"1099","article-title":"Deep neural networks with multi-branch architectures are intrinsically less non-convex","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.104949"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590386"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46257-8_29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2281535"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2281534"},{"key":"ref48","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref53","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref55","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Cai"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref57","article-title":"DARTS: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv:1806.09055"},{"key":"ref58","article-title":"Picking winning tickets before training by preserving gradient flow","author":"Wang","year":"2020","journal-title":"arXiv:2002.07376"},{"key":"ref59","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018","journal-title":"arXiv:1810.02340"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5220\/0012949000003837"},{"key":"ref61","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tanaka"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119856"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00447"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.135"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27413-8_47"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11045675.pdf?arnumber=11045675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:19:38Z","timestamp":1751091578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3581919","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}