{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:06:43Z","timestamp":1783530403932,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206271"],"award-info":[{"award-number":["62206271"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076195"],"award-info":[{"award-number":["62076195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101453"],"award-info":[{"award-number":["62101453"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["AUGA5710011522"],"award-info":[{"award-number":["AUGA5710011522"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFA0917600"],"award-info":[{"award-number":["2024YFA0917600"]}]},{"name":"Shenzhen Key Technical Projects","award":["JSGG20220831105801004"],"award-info":[{"award-number":["JSGG20220831105801004"]}]},{"name":"Shenzhen Key Technical Projects","award":["CJGJZD2022051714160501"],"award-info":[{"award-number":["CJGJZD2022051714160501"]}]},{"name":"Guangdong University Featured Innovation Program Project","award":["2024KTSCX026"],"award-info":[{"award-number":["2024KTSCX026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcsvt.2025.3539661","type":"journal-article","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T18:47:34Z","timestamp":1738954054000},"page":"6961-6973","source":"Crossref","is-referenced-by-count":2,"title":["Joint Memory Optimization for Continual Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0034-2065","authenticated-orcid":false,"given":"Zhiheng","family":"Ma","sequence":"first","affiliation":[{"name":"Faculty of Computility Microelectronics, Shenzhen University of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9746-5523","authenticated-orcid":false,"given":"Yaohui","family":"Ma","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0611-0636","authenticated-orcid":false,"given":"Xiaopeng","family":"Hong","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0157-1393","authenticated-orcid":false,"given":"Huiyun","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Computility Microelectronics, Shenzhen University of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3429-576X","authenticated-orcid":false,"given":"Shizhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref4","article-title":"A model or 603 exemplars: Towards memory-efficient class-incremental learning","author":"Zhou","year":"2022","journal-title":"arXiv:2205.13218"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref9","first-page":"14879","article-title":"Coresets via bilevel optimization for continual learning and streaming","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Borsos"},{"key":"ref10","first-page":"18309","article-title":"Advancing model pruning via bi-level optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref11","article-title":"What do compressed deep neural networks forget?","author":"Hooker","year":"2019","journal-title":"arXiv:1911.05248"},{"key":"ref12","article-title":"On differentiating parameterized argmin and argmax problems with application to bi-level optimization","author":"Gould","year":"2016","journal-title":"arXiv:1607.05447"},{"key":"ref13","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref14","first-page":"19655","article-title":"HYDRA: Pruning adversarially robust neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sehwag"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3355879"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376197"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01094"},{"key":"ref21","article-title":"Memory replay with data compression for continual learning","author":"Wang","year":"2022","journal-title":"arXiv:2202.06592"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"ref24","first-page":"1","article-title":"Progressive Voronoi diagram subdivision enables accurate data-free class-incremental learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01754"},{"key":"ref26","article-title":"Self-expansion of pre-trained models with mixture of adapters for continual learning","author":"Wang","year":"2024","journal-title":"arXiv:2403.18886"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref29","first-page":"5682","article-title":"S-prompts learning with pre-trained transformers: An Occam\u2019s Razor for domain incremental learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref30","article-title":"Steering prototypes with prompt-tuning for rehearsal-free continual learning","author":"Li","year":"2023","journal-title":"arXiv:2303.09447"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01439"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref34","article-title":"Continual learning via neural pruning","author":"Golkar","year":"2019","journal-title":"arXiv:1903.04476"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3382513"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262739"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304567"},{"key":"ref39","first-page":"6470","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"L\u00f3pez-Paz"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref42","article-title":"Vision transformer pruning","author":"Zhu","year":"2021","journal-title":"arXiv:2104.08500"},{"key":"ref43","first-page":"24101","article-title":"A fast post-training pruning framework for transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kwon"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref45","first-page":"26809","article-title":"PLATON: Pruning large transformer models with upper confidence bound of weight importance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref47","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":"ref48","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref49","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"2018","journal-title":"arXiv:1806.08342"},{"key":"ref50","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv:1902.08153"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01191"},{"key":"ref52","first-page":"26693","article-title":"Revisiting and advancing fast adversarial training through the lens of bi-level optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref53","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_23"},{"key":"ref57","first-page":"17","article-title":"Core50: A new dataset and benchmark for continuous object recognition","volume-title":"Proc. Conf. Robot Learn.","author":"Lomonaco"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref59","volume-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref60","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref61","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26216"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01053"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00164"},{"key":"ref66","first-page":"69054","article-title":"Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref67","first-page":"12022","article-title":"RanPAC: Random projections and pre-trained models for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"McDonnell"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01088"},{"key":"ref69","article-title":"Continual learning with tiny episodic memories","volume-title":"Proc. Workshop Multi-Task Lifelong Reinforcement Learn.","author":"Chaudhry"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01322"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11071401\/10877933.pdf?arnumber=10877933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:53:46Z","timestamp":1751910826000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10877933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":70,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3539661","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}