Feature Responsive LoRA: Towards Parameter-Efficient Transfer Learning for Self-Supervised Visual Models

Shanshan Wang, Xiaozheng Shen, Xun Yang, Ke Xu, Xingyi Zhang

Abstract: Low-Rank Adaptation (LoRA) is a widely utilized technique in topic of Parameter-Efficient Transfer Learning (PETL) which could use a limited number of trainable parameters to adapt the model to various downstream tasks. However, the setting of the locations and low-rank sizes in traditional LoRA relies heavily on the fixed and empirical values, which may hinder adaptability and lead to sharply decreasing performance, especially on some self-supervised pre-trained models. To alleviate this dilemma, we introduce a feature responsive LoRA (ResLoRA) method, a resource-efficient algorithm that automatically determines the LoRA modules’ required size based on the downstream task’s response. Firstly, we propose a Feature Decomposition loss (FD-loss) which leverages the feature singular values to mine the corresponding features of different downstream tasks, making the model parameters able to adequately represent downstream tasks. Subsequently, we leverage the Taylor expansion to measure the salience of the model parameters, then some high-efficient parameters with high significance could be leveraged to design a dynamically responsive LoRA. Specifically, the location and low-rank sizes of LoRA are determined based on the response parameters of the features for downstream tasks. Extensive experiments show that our ResLoRA achieves state-of-the-art performance, especially in the transfer capability of self-supervised models based on MoCo v3 and MAE. Our code is available at: https://github.com/wildboarman/ResLoRA.

External IDs:doi:10.1109/tcsvt.2025.3595896