Skip to yearly menu bar Skip to main content


Poster

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach

Wei Dong · Xing Zhang · Bihui Chen · Dawei Yan · Zhijun Lin · Qingsen Yan · Peng Wang · Yang Yang

Arch 4A-E Poster #143
[ ] [ Paper PDF ]
[ Poster
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT

Abstract:

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 https://github.com/zstarN70/RLRR.git.

Chat is not available.