{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T16:17:54Z","timestamp":1769271474929,"version":"3.49.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung Electronics Company Ltd.","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) grant funded by Korean Government (MSIT)","award":["2021-0-02068"],"award-info":[{"award-number":["2021-0-02068"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3375120","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T19:21:49Z","timestamp":1709839309000},"page":"37276-37287","source":"Crossref","is-referenced-by-count":2,"title":["Fast On-Device Learning Framework for Single-Image Super-Resolution"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8015-1558","authenticated-orcid":false,"given":"Seok Hee","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Gwanak-gu, Seoul, South Korea"}]},{"given":"Karam","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Gwanak-gu, Seoul, South Korea"}]},{"given":"Sunwoo","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Gwanak-gu, Seoul, South Korea"}]},{"given":"Hyun-Seung","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Yeongtong-gu, Suwon-si, South Korea"}]},{"given":"Kyuha","family":"Choi","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Yeongtong-gu, Suwon-si, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5297-4649","authenticated-orcid":false,"given":"Nam Ik","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Gwanak-gu, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00858"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3450494"},{"key":"ref11","first-page":"22941","article-title":"On-device training under 256kb memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lin"},{"key":"ref12","first-page":"1","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cai"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25874"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01196"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref17","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Han"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3149787"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00773"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.027"},{"key":"ref22","first-page":"5506","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref23","first-page":"27402","article-title":"Is integer arithmetic enough for deep learning training?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ghaffari"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00212"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475227"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00280"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_34"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956574"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_20"},{"key":"ref31","first-page":"5250","article-title":"Learning where to learn: Gradient sparsity in meta and continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Von Oswald"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.055"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_38"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01193"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00372"},{"key":"ref39","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evci"},{"key":"ref40","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref41","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref42","article-title":"How to train your MAML","author":"Antoniou","year":"2018","journal-title":"arXiv:1810.09502"},{"key":"ref43","first-page":"10","article-title":"Sharp-MAML: Sharpness-aware model-agnostic meta learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abbas"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01377"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00344"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00399"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_16"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00831"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00113"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00170"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00357"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref55","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv:1805.06085"},{"key":"ref56","first-page":"1","article-title":"Trained ternary quantization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref58","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1","author":"Courbariaux","year":"2016","journal-title":"arXiv:1602.02830"},{"key":"ref59","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref60","first-page":"1","article-title":"Scalable methods for 8-bit training of neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Banner"},{"key":"ref61","first-page":"1","article-title":"Mixed precision training of convolutional neural networks using integer operations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Das"},{"key":"ref62","first-page":"1","article-title":"Training and inference with integers in deep neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00096"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00099"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_22"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00519"},{"key":"ref68","first-page":"4646","article-title":"Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Mostafa"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01092"},{"key":"ref71","first-page":"3299","article-title":"meProp: Sparsified back propagation for accelerated deep learning with reduced overfitting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref72","first-page":"1","article-title":"Neural gradients are near-lognormal: Improved quantized and sparse training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chmiel"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref74","first-page":"1","article-title":"Rethinking the value of network pruning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01712"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.135"},{"key":"ref77","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"ref80","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10463025.pdf?arnumber=10463025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T13:00:02Z","timestamp":1711458002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10463025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3375120","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}