{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T22:52:46Z","timestamp":1779317566627,"version":"3.51.4"},"reference-count":38,"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\/4.0\/legalcode"}],"funder":[{"name":"National Centre of Science, Poland","award":["2020\/39\/B\/ST6\/01511"],"award-info":[{"award-number":["2020\/39\/B\/ST6\/01511"]}]},{"name":"National Centre of Science, Poland","award":["2021\/43\/O\/ST6\/02482"],"award-info":[{"award-number":["2021\/43\/O\/ST6\/02482"]}]},{"name":"National Centre of Science, Poland","award":["2022\/45\/B\/ST6\/02817"],"award-info":[{"award-number":["2022\/45\/B\/ST6\/02817"]}]},{"DOI":"10.13039\/501100011089","name":"PL-Grid Infrastructure","doi-asserted-by":"publisher","award":["PLG\/2023\/016393"],"award-info":[{"award-number":["PLG\/2023\/016393"]}],"id":[{"id":"10.13039\/501100011089","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Warsaw University of Technology Within the Excellence Initiative: Research University (IDUB) Programme"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3379148","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T19:21:25Z","timestamp":1710789685000},"page":"45309-45317","source":"Crossref","is-referenced-by-count":2,"title":["Looking Through the Past: Better Knowledge Retention for Generative Replay in Continual Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3505-3831","authenticated-orcid":false,"given":"Valeriya","family":"Khan","sequence":"first","affiliation":[{"name":"IDEAS NCBR, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4763-8381","authenticated-orcid":false,"given":"Sebastian","family":"Cygert","sequence":"additional","affiliation":[{"name":"IDEAS NCBR, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1156-5544","authenticated-orcid":false,"given":"Kamil","family":"Deja","sequence":"additional","affiliation":[{"name":"IDEAS NCBR, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8906","authenticated-orcid":false,"given":"Tomasz","family":"Trzcinski","sequence":"additional","affiliation":[{"name":"IDEAS NCBR, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2117-8679","authenticated-orcid":false,"given":"Bartlomiej","family":"Twardowski","sequence":"additional","affiliation":[{"name":"IDEAS NCBR, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00067"},{"key":"ref3","first-page":"1","article-title":"Continual learning with tiny episodic memories","volume-title":"Proc. ICML","author":"Chaudhry"},{"key":"ref4","first-page":"1","article-title":"Continual learning via neural pruning","volume-title":"Proc. Neuro AI. Workshop NIPS","author":"Golkar"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00041"},{"key":"ref7","first-page":"1","article-title":"Gans trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. NIPS","author":"Heusel"},{"key":"ref8","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS","author":"Hinton"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref10","article-title":"FearNet: Brain-inspired model for incremental learning","author":"Kemker","year":"2017","journal-title":"arXiv:1711.10563"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00375"},{"key":"ref12","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref14","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00121"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530587"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3213473"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1803839115"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8040093"},{"key":"ref26","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_31"},{"key":"ref28","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (PMLR)","author":"Rezende"},{"key":"ref29","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref30","article-title":"Assessing generative models via precision and recall","author":"Sajjadi","year":"2018","journal-title":"arXiv:1806.00035"},{"key":"ref31","first-page":"1","article-title":"Pseudo-rehearsal for continual learning with normalizing flows","volume-title":"Proc. ICML","author":"Scardapane"},{"key":"ref32","first-page":"2990","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17866-2"},{"key":"ref34","article-title":"Generative replay with feedback connections as a general strategy for continual learning","author":"van de Ven","year":"2018","journal-title":"arXiv:1809.10635"},{"key":"ref35","first-page":"1","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"Proc. ICLR","author":"Yoon"},{"key":"ref36","first-page":"1","article-title":"Reinforced continual learning","volume-title":"Proc. NIPS","author":"Xu"},{"key":"ref37","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3600-y"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10474374.pdf?arnumber=10474374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T20:07:12Z","timestamp":1712002032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10474374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3379148","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}