{"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/reviving-undersampling-for-long-tailed","title":"Reviving Undersampling for Long-Tailed Learning","arxiv_id":"2401.16811","date":"2024-01-30","proceeding":null,"authors":["Hao Yu","Yingxiao Du","Jianxin Wu"],"abstract":"The training datasets used in long-tailed recognition are extremely unbalanced, resulting in significant variation in per-class accuracy across categories. Prior works mostly used average accuracy to evaluate their algorithms, which easily ignores those worst-performing categories. In this paper, we aim to enhance the accuracy of the worst-performing categories and utilize the harmonic mean and geometric mean to assess the model's performance. We revive the balanced undersampling idea to achieve this goal. In few-shot learning, balanced subsets are few-shot and will surely under-fit, hence it is not used in modern long-tailed learning. But, we find that it produces a more equitable distribution of accuracy across categories with much higher harmonic and geometric mean accuracy, and, but lower average accuracy. Moreover, we devise a straightforward model ensemble strategy, which does not result in any additional overhead and achieves improved harmonic and geometric mean while keeping the average accuracy almost intact when compared to state-of-the-art long-tailed learning methods. We validate the effectiveness of our approach on widely utilized benchmark datasets for long-tailed learning. Our code is at \\href{https://github.com/yuhao318/BTM/}{https://github.com/yuhao318/BTM/}.","url_abs":"https://arxiv.org/abs/2401.16811v1","url_pdf":"https://arxiv.org/pdf/2401.16811v1.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":"reviving-undersampling-for-long-tailed","repo_url":"https://github.com/yuhao318/btm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reviving-undersampling-for-long-tailed","repo_url":"https://github.com/yuhao318/atomic_feature_mimicking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot 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}