ChangeDINO: DINOv3-Driven Building Change Detection in Optical Remote Sensing Imagery

TL;DR

ChangeDINO introduces a multiscale Siamese framework leveraging semantic-rich features from DINOv3 for robust building change detection in optical remote sensing images, outperforming existing methods across multiple benchmarks.

Contribution

It presents a novel end-to-end architecture that fuses features from a frozen DINOv3 model with a spatial-spectral transformer decoder for improved change detection.

Findings

Outperforms state-of-the-art methods in IoU and F1 scores.

Effective in small datasets and under challenging conditions.

Ablation studies validate each component's contribution.

Abstract

Remote sensing change detection (RSCD) aims to identify surface changes from co-registered bi-temporal images. However, many deep learning-based RSCD methods rely solely on change-map annotations and underuse the semantic information in non-changing regions, which limits robustness under illumination variation, off-nadir views, and scarce labels. This article introduces ChangeDINO, an end-to-end multiscale Siamese framework for optical building change detection. The model fuses a lightweight backbone stream with features transferred from a frozen DINOv3, yielding semantic- and context-rich pyramids even on small datasets. A spatial-spectral differential transformer decoder then exploits multi-scale absolute differences as change priors to highlight true building changes and suppress irrelevant responses. Finally, a learnable morphology module refines the upsampled logits to recover clean boundaries. Experiments on four public benchmarks show that ChangeDINO consistently outperforms recent state-of-the-art methods in IoU and F1, and ablation studies confirm the effectiveness of each component. The source code is available at https://github.com/chingheng0808/ChangeDINO.