{"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/scalable-transfer-learning-with-expert-models","title":"Scalable Transfer Learning with Expert Models","arxiv_id":"2009.13239","date":"2020-09-28","proceeding":"ICLR 2021 1","authors":["Joan Puigcerver","Carlos Riquelme","Basil Mustafa","Cedric Renggli","André Susano Pinto","Sylvain Gelly","Daniel Keysers","Neil Houlsby"],"abstract":"Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually generic, and are not tailored to a particular distribution of downstream tasks. We explore the use of expert representations for transfer with a simple, yet effective, strategy. We train a diverse set of experts by exploiting existing label structures, and use cheap-to-compute performance proxies to select the relevant expert for each target task. This strategy scales the process of transferring to new tasks, since it does not revisit the pre-training data during transfer. Accordingly, it requires little extra compute per target task, and results in a speed-up of 2-3 orders of magnitude compared to competing approaches. Further, we provide an adapter-based architecture able to compress many experts into a single model. We evaluate our approach on two different data sources and demonstrate that it outperforms baselines on over 20 diverse vision tasks in both cases.","url_abs":"https://arxiv.org/abs/2009.13239v1","url_pdf":"https://arxiv.org/pdf/2009.13239v1.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-vtab-1k-1","task":"Image Classification","dataset":"VTAB-1k","model":"ScalableExperts (I21k+JFT)","rank_in_archive_order":8,"of":34,"metrics":{"Top-1 Accuracy":"72.3"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.13239","atlas_url":"https://app.syntology.ai/?focus=2009.13239","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}