Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
arxiv(2024)
摘要
Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to
adeptly tailor a model to downstream tasks by learning a minimal set of new
adaptation parameters while preserving the frozen majority of pre-trained
parameters. Striking a balance between retaining the generalizable
representation capacity of the pre-trained model and acquiring task-specific
features poses a key challenge. Currently, there is a lack of focus on guiding
this delicate trade-off. In this study, we approach the problem from the
perspective of Singular Value Decomposition (SVD) of pre-trained parameter
matrices, providing insights into the tuning dynamics of existing methods.
Building upon this understanding, we propose a Residual-based Low-Rank
Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances
flexibility in parameter tuning but also ensures that new parameters do not
deviate excessively from the pre-trained model through a residual design.
Extensive experiments demonstrate that our method achieves competitive
performance across various downstream image classification tasks, all while
maintaining comparable new parameters. We believe this work takes a step
forward in offering a unified perspective for interpreting existing methods and
serves as motivation for the development of new approaches that move closer to
effectively considering the crucial trade-off mentioned above. Our code is
available at
\href{https://github.com/zstarN70/RLRR.git}{https://github.com/zstarN70/RLRR.git}.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要