{"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/sct-a-simple-baseline-for-parameter-efficient","title":"SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels","arxiv_id":"2309.08513","date":"2023-09-15","proceeding":null,"authors":["Henry Hengyuan Zhao","Pichao Wang","Yuyang Zhao","Hao Luo","Fan Wang","Mike Zheng Shou"],"abstract":"Pre-trained vision transformers have strong representation benefits to various downstream tasks. Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, and their experiments demonstrate that tuning only 1\\% extra parameters could surpass full fine-tuning in low-data resource scenarios. However, these methods overlook the task-specific information when fine-tuning diverse downstream tasks. In this paper, we propose a simple yet effective method called \"Salient Channel Tuning\" (SCT) to leverage the task-specific information by forwarding the model with the task images to select partial channels in a feature map that enables us to tune only 1/8 channels leading to significantly lower parameter costs. Experiments on 19 visual transfer learning downstream tasks demonstrate that our SCT outperforms full fine-tuning on 18 out of 19 tasks by adding only 0.11M parameters of the ViT-B, which is 780$\\times$ fewer than its full fine-tuning counterpart. Furthermore, experiments on domain generalization and few-shot classification further demonstrate the effectiveness and generic of our approach. The code is available at https://github.com/showlab/SCT.","url_abs":"https://arxiv.org/abs/2309.08513v5","url_pdf":"https://arxiv.org/pdf/2309.08513v5.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":"sct-a-simple-baseline-for-parameter-efficient","repo_url":"https://github.com/showlab/sct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"sct-a-simple-baseline-for-parameter-efficient","repo_url":"https://github.com/zhaohengyuan1/sct","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.08513","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}