SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels.
Saved in:
| Title: | SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels. |
|---|---|
| Authors: | Zhao, Henry Hengyuan1 (AUTHOR), Wang, Pichao2 (AUTHOR), Zhao, Yuyang1 (AUTHOR), Luo, Hao3 (AUTHOR), Wang, Fan2 (AUTHOR), Shou, Mike Zheng1 (AUTHOR) mike.zheng.shou@gmail.com |
| Source: | International Journal of Computer Vision. Mar2024, Vol. 132 Issue 3, p731-749. 19p. |
| Subjects: | Transformer models, Stimulus generalization, Generalization |
| Abstract: | Pre-trained vision transformers have strong representations benefit 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 outperform full fine-tuning on 18 out of 19 tasks in the VTAB-1K benchmark by adding only 0.11M parameters of the ViT-B, which is 780 × fewer than its full fine-tuning counterpart. Furthermore, experiments on domain generalization and few-shot learning surpass other PEFT methods with lower parameter costs, demonstrating our proposed tuning technique's strong capability and effectiveness in the low-data regime. The code will be available at https://github.com/zhaohengyuan1/SCT.git [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Pre-trained vision transformers have strong representations benefit 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 outperform full fine-tuning on 18 out of 19 tasks in the VTAB-1K benchmark by adding only 0.11M parameters of the ViT-B, which is 780 × fewer than its full fine-tuning counterpart. Furthermore, experiments on domain generalization and few-shot learning surpass other PEFT methods with lower parameter costs, demonstrating our proposed tuning technique's strong capability and effectiveness in the low-data regime. The code will be available at https://github.com/zhaohengyuan1/SCT.git [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 09205691 |
| DOI: | 10.1007/s11263-023-01918-3 |
