{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:11:56Z","timestamp":1788844316221,"version":"build-2803163510"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Agence Nationale de la Recherche","award":["ANR-23-PECL-0006"],"award-info":[{"award-number":["ANR-23-PECL-0006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00096","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:18:40Z","timestamp":1788808720000},"page":"771-781","source":"Crossref","is-referenced-by-count":0,"title":["Dual Model Learning for Efficient and Effective Visual Services"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9649-7127","authenticated-orcid":false,"given":"Mehdi","family":"Acheli","sequence":"first","affiliation":[{"name":"Telecom SudParis, Institut Polytechnique de Paris","place":["Palaiseau, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0451-532X","authenticated-orcid":false,"given":"Walid","family":"Gaaloul","sequence":"additional","affiliation":[{"name":"Telecom SudParis, Institut Polytechnique de Paris","place":["Palaiseau, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2025.101553"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2016.145"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"ref5","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14244877"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1037\/a0026179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-62604-2.00022-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci14090902"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2023.1230576"},{"issue":"1","key":"ref11","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref13","article-title":"Forward thinking: Building and training neural networks one layer at a time","author":"Hettinger","year":"2017","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Freezeout: Accelerate training by progressively freezing layers","author":"Brock","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00205"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09592-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587451"},{"key":"ref18","article-title":"Sparse networks from scratch: Faster training without losing performance","author":"Dettmers","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Dynamic sparse training: Find efficient sparse network from scratch with trainable masked layers","author":"Liu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Truly sparse neural networks at scale","author":"Curci","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3234761"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1515\/9783111376776-010"},{"key":"ref24","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3233\/ia-240035"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref29","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"4057","article-title":"Unified scaling laws for routed language models","volume-title":"International conference on machine learning","author":"Clark","year":"2022"},{"key":"ref31","article-title":"Routing networks: Adaptive selection of non-linear functions for multi-task learning","author":"Rosenbaum","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref33","volume-title":"Pytorch image models","author":"Wightman","year":"2019"},{"key":"ref34","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","article-title":"Adafisher: Adaptive second order optimization via fisher information","author":"Gomes","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref38","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Resnet strikes back: An improved training procedure in timm","author":"Wightman","year":"2021","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Large batch optimization for deep learning: Training bert in 76 minutes","author":"You","year":"2019","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref46","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref48","article-title":"Multigrain: a unified image embedding for classes and instances","author":"Berman","year":"2019","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128998"},{"key":"ref50","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac3ae8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4135\/9781412983907.n1717"},{"key":"ref54","article-title":"Autoaugment: Learning augmentation policies from data","author":"Cubuk","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2026 IEEE International Conference on Web Services (ICWS)","location":"Sydney, Australia","start":{"date-parts":[[2026,7,13]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["2026 IEEE International Conference on Web Services (ICWS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11670018\/11670022\/11670115.pdf?arnumber=11670115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:53:10Z","timestamp":1788843190000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00096","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}