{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/continuous-learning-in-single-incremental","title":"Continuous Learning in Single-Incremental-Task Scenarios","arxiv_id":"1806.08568","date":"2018-06-22","proceeding":null,"authors":["Davide Maltoni","Vincenzo Lomonaco"],"abstract":"It was recently shown that architectural, regularization and rehearsal\nstrategies can be used to train deep models sequentially on a number of\ndisjoint tasks without forgetting previously acquired knowledge. However, these\nstrategies are still unsatisfactory if the tasks are not disjoint but\nconstitute a single incremental task (e.g., class-incremental learning). In\nthis paper we point out the differences between multi-task and\nsingle-incremental-task scenarios and show that well-known approaches such as\nLWF, EWC and SI are not ideal for incremental task scenarios. A new approach,\ndenoted as AR1, combining architectural and regularization strategies is then\nspecifically proposed. AR1 overhead (in term of memory and computation) is very\nsmall thus making it suitable for online learning. When tested on CORe50 and\niCIFAR-100, AR1 outperformed existing regularization strategies by a good\nmargin.","url_abs":"http://arxiv.org/abs/1806.08568v3","url_pdf":"http://arxiv.org/pdf/1806.08568v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"continuous-learning-in-single-incremental","repo_url":"https://github.com/ContinualAI/avalanche","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"ewc","method_name":"EWC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.08568","atlas_url":"https://app.syntology.ai/?focus=1806.08568","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}