EUVIMEDEUVIMED entdecken
Crossref

S2C: A Noise-Resistant Difference Learning Framework for Unsupervised Change Detection in VHR Remote Sensing Images

Lei Ding, Xibing Zuo, Haitao Guo, Jun Lu, Zhihui Gong, Xuanguang Liu, Jicang Lu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3596-3604

DOI: 10.1609/aaai.v40i5.37358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Lei Ding und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised Change Detection (UCD) in Very High Resolution (VHR) Remote Sensing (RS) images remains to be a difficult challenge due to the inherent spatio-temporal complexity within data. Inspired by recent advancements in Visual Foundation Models (VFMs) and Contrastive Learning (CL), this research aims to develop CL methodologies to translate implicit knowledge in VFM into change representations, thus eliminating the need for explicit supervision. To this end, we introduce a Semantic-to-Change (S2C) learning framework for UCD in VHR RS images. Differently from existing CL methodologies that typically focus on learning multi-temporal similarities, we introduce a novel triplet learning strategy that explicitly models temporal differences, which are crucial to the CD task. Furthermore, random spatial and spectral perturbations are introduced during training to enhance robustness to temporal noise. In addition, a grid sparsity regularization is defined to suppress insignificant changes, and an IoU-matching algorithm is developed to refine the CD results. Experiments on three benchmark CD datasets demonstrate that the proposed S2C learning framework achieves significant improvements in accuracy, surpassing current state-of-the-art by over 31%, 9% and 23%, respectively. It also demonstrates robustness and sample efficiency, suitable for training and adaptation of various VFMs or backbone neural networks.

Zitieren

APA

Ding, L., Zuo, X., Guo, H., Lu, J., Gong, Z., Liu, X., & Lu, J. (2026). S2C: A Noise-Resistant Difference Learning Framework for Unsupervised Change Detection in VHR Remote Sensing Images. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3596-3604. https://doi.org/10.1609/aaai.v40i5.37358

Vancouver

Ding L, Zuo X, Guo H, Lu J, Gong Z, Liu X, et al. S2C: A Noise-Resistant Difference Learning Framework for Unsupervised Change Detection in VHR Remote Sensing Images. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3596-3604. doi:10.1609/aaai.v40i5.37358

BibTeX
@article{Ding2026,
  author = {Ding, Lei and Zuo, Xibing and Guo, Haitao and Lu, Jun and Gong, Zhihui and Liu, Xuanguang and Lu, Jicang},
  title = {S2C: A Noise-Resistant Difference Learning Framework for Unsupervised Change Detection in VHR Remote Sensing Images},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3596--3604},
  doi = {10.1609/aaai.v40i5.37358}
}
Kostenlos starten →