{"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/refocusing-is-key-to-transfer-learning","title":"TOAST: Transfer Learning via Attention Steering","arxiv_id":"2305.15542","date":"2023-05-24","proceeding":null,"authors":["Baifeng Shi","Siyu Gai","Trevor Darrell","Xin Wang"],"abstract":"Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we explore refocusing model attention for transfer learning. We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, selects task-relevant features in the output, and feeds those features back to the model to steer the attention to the task-specific features. By refocusing the attention only, TOAST achieves state-of-the-art results on a number of transfer learning benchmarks, while having a small number of tunable parameters. Compared to fully fine-tuning, LoRA, and prompt tuning, TOAST substantially improves performance across a range of fine-grained visual classification datasets (e.g., 81.1% -> 86.2% on FGVC). TOAST also outperforms the fully fine-tuned Alpaca and Vicuna models on instruction-following language generation. Code is available at https://github.com/bfshi/TOAST.","url_abs":"https://arxiv.org/abs/2305.15542v2","url_pdf":"https://arxiv.org/pdf/2305.15542v2.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":"refocusing-is-key-to-transfer-learning","repo_url":"https://github.com/bfshi/toast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.15542","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}