PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dong, Sijun, Hu, Yuxuan, Wang, LiBo, Chen, Geng, Meng, Xiaoliang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916946679693312
author Dong, Sijun
Hu, Yuxuan
Wang, LiBo
Chen, Geng
Meng, Xiaoliang
author_facet Dong, Sijun
Hu, Yuxuan
Wang, LiBo
Chen, Geng
Meng, Xiaoliang
contents To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built upon Vision Foundation Models (VFMs) with Parameter-Efficient Fine-Tuning (PEFT). At its core, PeftCD employs a weight-sharing Siamese encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated. This design enables highly efficient task adaptation by training only a minimal set of additional parameters. To fully unlock the potential of VFMs, we investigate two leading backbones: the Segment Anything Model v2 (SAM2), renowned for its strong segmentation priors, and DINOv3, a state-of-the-art self-supervised representation learner. The framework is complemented by a deliberately lightweight decoder, ensuring the focus remains on the powerful feature representations from the backbones. Extensive experiments demonstrate that PeftCD achieves state-of-the-art performance across multiple public datasets, including SYSU-CD (IoU 73.81%), WHUCD (92.05%), MSRSCD (64.07%), MLCD (76.89%), CDD (97.01%), S2Looking (52.25%) and LEVIR-CD (85.62%), with notably precise boundary delineation and strong suppression of pseudo-changes. In summary, PeftCD presents an optimal balance of accuracy, efficiency, and generalization. It offers a powerful and scalable paradigm for adapting large-scale VFMs to real-world remote sensing change detection applications. The code and pretrained models will be released at https://github.com/dyzy41/PeftCD.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09572
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
Dong, Sijun
Hu, Yuxuan
Wang, LiBo
Chen, Geng
Meng, Xiaoliang
Computer Vision and Pattern Recognition
To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built upon Vision Foundation Models (VFMs) with Parameter-Efficient Fine-Tuning (PEFT). At its core, PeftCD employs a weight-sharing Siamese encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated. This design enables highly efficient task adaptation by training only a minimal set of additional parameters. To fully unlock the potential of VFMs, we investigate two leading backbones: the Segment Anything Model v2 (SAM2), renowned for its strong segmentation priors, and DINOv3, a state-of-the-art self-supervised representation learner. The framework is complemented by a deliberately lightweight decoder, ensuring the focus remains on the powerful feature representations from the backbones. Extensive experiments demonstrate that PeftCD achieves state-of-the-art performance across multiple public datasets, including SYSU-CD (IoU 73.81%), WHUCD (92.05%), MSRSCD (64.07%), MLCD (76.89%), CDD (97.01%), S2Looking (52.25%) and LEVIR-CD (85.62%), with notably precise boundary delineation and strong suppression of pseudo-changes. In summary, PeftCD presents an optimal balance of accuracy, efficiency, and generalization. It offers a powerful and scalable paradigm for adapting large-scale VFMs to real-world remote sensing change detection applications. The code and pretrained models will be released at https://github.com/dyzy41/PeftCD.
title PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.09572