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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cheng, Ching-Heng, Hsu, Chih-Chung
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915628556746752
author Cheng, Ching-Heng
Hsu, Chih-Chung
author_facet Cheng, Ching-Heng
Hsu, Chih-Chung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16322
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChangeDINO: DINOv3-Driven Building Change Detection in Optical Remote Sensing Imagery
Cheng, Ching-Heng
Hsu, Chih-Chung
Computer Vision and Pattern Recognition
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.
title ChangeDINO: DINOv3-Driven Building Change Detection in Optical Remote Sensing Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.16322