Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2025

Abstract

Training large foundation models of remote-sensing (RS) images is almost impossible due to the limited and long-tailed data problems. Fine-tuning natural image pre-trained models on RS images is a straightforward solution. To reduce computational costs and improve performance on tail classes, existing methods apply parameter-efficient fine-tuning (PEFT) techniques, such as LoRA and AdaptFormer. However, we observe that fixed hyperparameters -- such as intra-layer positions, layer depth, and scaling factors, can considerably hinder PEFT performance, as fine-tuning on RS images proves highly sensitive to these settings. To address this, we propose MetaPEFT, a method incorporating adaptive scalers that dynamically adjust module influence during fine-tuning. MetaPEFT dynamically adjusts three key factors of PEFT on RS images: module insertion, layer selection, and module-wise learning rates, which collectively control the influence of PEFT modules across the network. We conduct extensive experiments on three transfer-learning scenarios and five datasets. The results show that MetaPEFT achieves state-of-the-art performance in cross-spectral adaptation, requiring only a small amount of trainable parameters and improving tail-class accuracy significantly. Our code is available in the supplementary materials for review.

Discipline

Artificial Intelligence and Robotics | Computer Engineering

Areas of Excellence

Digital transformation

Publication

Proceedings of the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR'25, Nashville, USA, June 11-15

First Page

1

Last Page

11

Publisher

CVPR

City or Country

Nashville

Download

Share

COinS