{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T19:20:21Z","timestamp":1787944821271,"version":"build-2784847793"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"crossref","award":["JCZRLH202500612"],"award-info":[{"award-number":["JCZRLH202500612"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Advantages Discipline Group (Medical) Project in Higher Education of Hubei Province","award":["2025XKQT31"],"award-info":[{"award-number":["2025XKQT31"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3723541","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T19:07:30Z","timestamp":1786648050000},"page":"129347-129360","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchy-Aligned Learning Rates for Vision Networks"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5329-5656","authenticated-orcid":false,"given":"Qiang","family":"He","sequence":"first","affiliation":[{"name":"Huazhong Agricultural University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiu-Hao","family":"Zong","sequence":"additional","affiliation":[{"name":"Hubei University of Medicine","place":["Shiyan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9332-2292","authenticated-orcid":false,"given":"Yi-Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"Hubei University of Medicine","place":["Shiyan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8300-1054","authenticated-orcid":false,"given":"Xu","family":"Meng","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8078-4401","authenticated-orcid":false,"given":"Hong-Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3974-9206","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hubei University of Medicine","place":["Shiyan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11140-w"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.113"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3689827"},{"key":"ref9","article-title":"Large batch training of convolutional networks","author":"You","year":"2017","journal-title":"arXiv:1708.03888"},{"key":"ref10","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"You"},{"key":"ref11","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref12","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref13","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3263393"},{"key":"ref15","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00137"},{"key":"ref17","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014","journal-title":"arXiv:1404.5997"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref20","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref22","first-page":"2171","article-title":"Scalable Bayesian optimization using deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Snoek"},{"issue":"1","key":"ref23","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"Li","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","article-title":"Population based training of neural networks","author":"Jaderberg","year":"2017","journal-title":"arXiv:1711.09846"},{"key":"ref25","article-title":"An exponential learning rate schedule for deep learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929465"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"issue":"61","key":"ref28","first-page":"2121","article-title":"Adaptive subgradient methods for Online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4135\/9781412983907.n1717"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref31","article-title":"AutoLRS: Automatic learning-rate schedule by Bayesian optimization on the fly","author":"Jin","year":"2021","journal-title":"arXiv:2105.10762"},{"key":"ref32","article-title":"Learning to schedule learning rate with graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xiong"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3561415"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref37","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0084"},{"key":"ref39","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","volume":"9","author":"Glorot"},{"key":"ref40","article-title":"A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gotmare"},{"key":"ref41","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref42","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"29","author":"Vinyals"},{"key":"ref43","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref47","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8137.1912.tb05611.x"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/1932409.JSTOR1932409"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2013851"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11655050.pdf?arnumber=11655050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T19:09:52Z","timestamp":1787944192000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11655050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3723541","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}