{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:54:07Z","timestamp":1777654447267,"version":"3.51.4"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Deep neural networks often forget previously learned information when trained sequentially on new objectives, a phenomenon known as catastrophic forgetting. Existing generative strategies combat this issue by randomly sampling rehearsal examples from a generative model. Such an approach contradicts buffer-based approaches where sampling strategy plays an important role. We propose to bridge this gap and benefit from the combination of DDPM trained on the previous task and the classifier guidance technique to actively generate rehearsal examples specifically designed to minimize forgetting in the currently trained classifier. Our experimental results show that GUIDE significantly reduces catastrophic forgetting, outperforming conventional random sampling approaches and surpassing recent state-of-the-art methods in continual learning with generative replay, and buffer-based rehearsal.<\/jats:p>","DOI":"10.3233\/faia251238","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:55:33Z","timestamp":1761126933000},"source":"Crossref","is-referenced-by-count":2,"title":["GUIDE: Guidance-Based Incremental Learning with Diffusion Models"],"prefix":"10.3233","author":[{"given":"Bartosz","family":"Cywi\u0144ski","sequence":"first","affiliation":[{"name":"Warsaw University of Technology"},{"name":"IDEAS Research Institute"}]},{"given":"Kamil","family":"Deja","sequence":"additional","affiliation":[{"name":"Warsaw University of Technology"},{"name":"IDEAS Research Institute"}]},{"given":"Tomasz","family":"Trzci\u0144ski","sequence":"additional","affiliation":[{"name":"Warsaw University of Technology"},{"name":"IDEAS Research Institute"}]},{"given":"Bart\u0142omiej","family":"Twardowski","sequence":"additional","affiliation":[{"name":"IDEAS Research Institute"},{"name":"CVC Universitat Autonoma de Barcelona"}]},{"given":"\u0141ukasz","family":"Kuci\u0144ski","sequence":"additional","affiliation":[{"name":"IDEAS NCBR"},{"name":"University of Warsaw"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:55:34Z","timestamp":1761126934000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251238","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}