{"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/co-tuning-for-transfer-learning","title":"Co-Tuning for Transfer Learning","arxiv_id":null,"date":"2020-12-01","proceeding":"NeurIPS 2020 12","authors":["Kaichao You","Zhi Kou","Mingsheng Long","Jianmin Wang"],"abstract":"Fine-tuning pre-trained deep neural networks (DNNs) to a target dataset, also known as transfer learning, is widely used in computer vision and NLP. Because task-specific layers mainly contain categorical information and categories vary with datasets, practitioners only \\textit{partially} transfer pre-trained models by discarding task-specific layers and fine-tuning bottom layers. However, it is a reckless loss to simply discard task-specific parameters who take up as many as $20\\%$ of the total parameters in pre-trained models. To \\textit{fully} transfer pre-trained models, we propose a two-step framework named \\textbf{Co-Tuning}: (i)  learn the relationship between source categories and target categories from the pre-trained model and calibrated predictions; (ii) target labels (one-hot labels), as well as source labels (probabilistic labels) translated by the category relationship, collaboratively supervise the fine-tuning process. A simple instantiation of the framework shows strong empirical results in four visual classification tasks and one NLP classification task, bringing up to $20\\%$ relative improvement. While state-of-the-art fine-tuning techniques mainly focus on how to impose regularization when data are not abundant, Co-Tuning works not only in medium-scale datasets (100 samples per class) but also in large-scale datasets (1000 samples per class) where regularization-based methods bring no gains over the vanilla fine-tuning. Co-Tuning relies on a typically valid assumption that the pre-trained dataset is diverse enough, implying its broad application area.","url_abs":"http://proceedings.neurips.cc/paper/2020/hash/c8067ad1937f728f51288b3eb986afaa-Abstract.html","url_pdf":"http://proceedings.neurips.cc/paper/2020/file/c8067ad1937f728f51288b3eb986afaa-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":"co-tuning-for-transfer-learning","repo_url":"https://github.com/thuml/CoTuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"co-tuning-for-transfer-learning","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/transfer-learning-on-coco70","task":"Transfer Learning","dataset":"COCO70","model":"Co-Tuning","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"85.65"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}