{"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/coarsely-labeled-data-for-better-few-shot","title":"Coarsely-Labeled Data for Better Few-Shot Transfer","arxiv_id":null,"date":"2021-01-01","proceeding":"ICCV 2021 10","authors":["Cheng Perng Phoo","Bharath Hariharan"],"abstract":"    Few-shot learning is based on the premise that labels are expensive, especially when they are fine-grained and require expertise. But coarse labels might be easy to acquire and thus abundant. We present a representation learning approach - PAS that allows few-shot learners to leverage coarsely-labeled data available before evaluation. Inspired by self-training, we label the additional data using a teacher trained on the base dataset and filter the teacher's prediction based on the coarse labels; a new student representation is then trained on the base dataset and the pseudo-labeled dataset. PAS is able to produce a representation that consistently and significantly outperforms the baselines in 3 different datasets. Code is available at https://github.com/cpphoo/PAS.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2021/html/Phoo_Coarsely-Labeled_Data_for_Better_Few-Shot_Transfer_ICCV_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2021/papers/Phoo_Coarsely-Labeled_Data_for_Better_Few-Shot_Transfer_ICCV_2021_paper.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":"coarsely-labeled-data-for-better-few-shot","repo_url":"https://github.com/cpphoo/pas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}