{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:47:40Z","timestamp":1776750460883,"version":"3.51.2"},"reference-count":41,"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\/501100003725","name":"National Research Foundation of Korea (NRF), Republic of Korea","doi-asserted-by":"publisher","award":["RS-2024-00441473"],"award-info":[{"award-number":["RS-2024-00441473"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF), Republic of Korea","doi-asserted-by":"publisher","award":["RS-2024-00401234"],"award-info":[{"award-number":["RS-2024-00401234"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF), Republic of Korea","doi-asserted-by":"publisher","award":["RS-2024-00406006"],"award-info":[{"award-number":["RS-2024-00406006"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF), Republic of Korea","doi-asserted-by":"publisher","award":["RS-2025-12872969"],"award-info":[{"award-number":["RS-2025-12872969"]}],"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":[[2026]]},"DOI":"10.1109\/access.2026.3682854","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:00:05Z","timestamp":1775851205000},"page":"56900-56918","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Compression of ResNet: An 8.33\u00d7 Reduction With 90.5% Accuracy Retention for Edge Deployment"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0554-585X","authenticated-orcid":false,"given":"Tu Tien","family":"Ngo","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5862-8511","authenticated-orcid":false,"given":"Nguyen","family":"Bich","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-4366","authenticated-orcid":false,"given":"Pham the","family":"Bao","sequence":"additional","affiliation":[{"name":"Information Science Faculty, Saigon University, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5797-1161","authenticated-orcid":false,"given":"Son Ngoc","family":"Truong","sequence":"additional","affiliation":[{"name":"Faculty of Electrical and Electronics Engineering, HCMC University of Technology and Engineering, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9990-9331","authenticated-orcid":false,"given":"Huan Minh","family":"Vo","sequence":"additional","affiliation":[{"name":"Faculty of Electrical and Electronics Engineering, HCMC University of Technology and Engineering, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6129-5856","authenticated-orcid":false,"given":"Khoa van","family":"Pham","sequence":"additional","affiliation":[{"name":"Faculty of Electrical and Electronics Engineering, HCMC University of Technology and Engineering, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1518-7037","authenticated-orcid":false,"given":"Kyeong-Sik","family":"Min","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202000115"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622877"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s23031279"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref6","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref10","first-page":"7948","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Banner"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref13","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.71"},{"key":"ref17","first-page":"442","article-title":"Tensorizing neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Novikov"},{"key":"ref18","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3776588"},{"key":"ref21","first-page":"11711","article-title":"MCUNet: Tiny deep learning on IoT devices","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1602.07360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref25","first-page":"407","article-title":"Flynet: Max it, excite it, quantize it","volume-title":"Proc. BMVC","author":"Guerra"},{"key":"ref26","article-title":"GhostNetV3: Exploring the training strategies for compact models","author":"Liu","year":"2024","journal-title":"arXiv:2404.11202"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref29","article-title":"IFormer: Integrating ConvNet and transformer for mobile application","author":"Zheng","year":"2025","journal-title":"arXiv:2501.15369"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"ref32","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"},{"key":"ref34","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref35","article-title":"Tiny imagenet visual recognition challenge","author":"Le","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref37","first-page":"2623","article-title":"Optuna: A next-generation hyperparameter optimization framework","volume-title":"Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","author":"Swantje"},{"key":"ref38","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref39","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":"ref40","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"Cai","year":"2019","journal-title":"arXiv:1908.09791"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11479314.pdf?arnumber=11479314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:20:18Z","timestamp":1776748818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11479314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3682854","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}