DynamicEarth: How Far Are We from Open-Vocabulary Change Detection?
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6279-6287
DOI: 10.1609/aaai.v40i8.37554 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kaiyu Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
Monitoring Earth's evolving land covers requires methods capable of detecting changes across a wide range of categories and contexts. Existing change detection methods are hindered by their dependency on predefined classes, reducing their effectiveness in open-world applications. To address this issue, we introduce open-vocabulary change detection (OVCD), a novel task that bridges vision and language to detect changes across any category. Considering the lack of high-quality data and annotation, we propose two training-free frameworks, M-C-I and I-M-C, which leverage and integrate off-the-shelf foundation models for the OVCD task. The insight behind the M-C-I~framework is to discover all potential changes and then classify these changes, while the insight of I-M-C~framework is to identify all targets of interest and then determine whether their states have changed. Based on these two frameworks, we instantiate to obtain several methods, e.g., SAM-DINOv2-SegEarth-OV, Grounding-DINO-SAM2-DINO, etc. Extensive evaluations on 4 benchmark datasets demonstrate the superior generalization and robustness of our OVCD methods over existing supervised and unsupervised methods. To support continued exploration, we release DynamicEarth, a dedicated codebase designed to advance research and application of OVCD.
Zitieren
APA
Li, K., Cao, X., Deng, Y., Pang, C., Xin, Z., Qiao, H., Gong, T., Meng, D., & Wang, Z. (2026). DynamicEarth: How Far Are We from Open-Vocabulary Change Detection?. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6279-6287. https://doi.org/10.1609/aaai.v40i8.37554
Vancouver
Li K, Cao X, Deng Y, Pang C, Xin Z, Qiao H, et al. DynamicEarth: How Far Are We from Open-Vocabulary Change Detection?. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6279-6287. doi:10.1609/aaai.v40i8.37554
BibTeX
@article{Li2026,
author = {Li, Kaiyu and Cao, Xiangyong and Deng, Yupeng and Pang, Chao and Xin, Zepeng and Qiao, Hui and Gong, Tieliang and Meng, Deyu and Wang, Zhi},
title = {DynamicEarth: How Far Are We from Open-Vocabulary Change Detection?},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6279--6287},
doi = {10.1609/aaai.v40i8.37554}
}
EUVIMED