{"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/revisiting-fine-tuning-for-few-shot-learning","title":"Revisiting Fine-tuning for Few-shot Learning","arxiv_id":"1910.00216","date":"2019-10-01","proceeding":null,"authors":["Akihiro Nakamura","Tatsuya Harada"],"abstract":"Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks can easily overfit to novel examples if they are simply fine-tuned using only a few examples. In this study, we show that in the commonly used low-resolution mini-ImageNet dataset, the fine-tuning method achieves higher accuracy than common few-shot learning algorithms in the 1-shot task and nearly the same accuracy as that of the state-of-the-art algorithm in the 5-shot task. We then evaluate our method with more practical tasks, namely the high-resolution single-domain and cross-domain tasks. With both tasks, we show that our method achieves higher accuracy than common few-shot learning algorithms. We further analyze the experimental results and show that: 1) the retraining process can be stabilized by employing a low learning rate, 2) using adaptive gradient optimizers during fine-tuning can increase test accuracy, and 3) test accuracy can be improved by updating the entire network when a large domain-shift exists between base and novel classes.","url_abs":"https://arxiv.org/abs/1910.00216v2","url_pdf":"https://arxiv.org/pdf/1910.00216v2.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":"category-agnostic-pose-estimation","task_name":"Category-Agnostic Pose Estimation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/category-agnostic-pose-estimation-on-mp100","task":"Category-Agnostic Pose Estimation","dataset":"MP100","model":"Finetune","rank_in_archive_order":3,"of":5,"metrics":{"Mean PCK@0.2 - 1shot":"63.58"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.00216","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}