Uncertainty-Aware Label-Efficient Landslide Segmentation in Open-Pit Mines via Transformer Transfer Learning and Active Learning
Remote Sensing · 01.06.2026 · 18 (11) · 1774
DOI: 10.3390/rs18111774 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 01.06.2026. Verfasst von Haiying Li und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Program of National Natural Science Foundation of China.
Abstract (Originalsprache)
Reliable landslide mapping in active mining regions is constrained by two coupled issues: severe domain shift from public datasets and extremely limited local annotations. In line with Transformer-centric intelligent interpretation of complex remote-sensing scenes, this study proposes a label-efficient transfer segmentation framework from a public source corpus to target open-pit mines built on SegFormer with a lightweight hybrid adapter that couples global context modeling with mining-specific directional cues. The pipeline combines source-domain Transformer pre-training, class-conditional feature alignment, Bayesian uncertainty estimation, and human-guided active learning. First, the backbone is pre-trained on the GDCLD source domain to learn transferable landslide morphology priors. Second, a joint optimization stage with class-conditional alignment reduces source and target embedding discrepancy during adaptation. Third, Monte Carlo dropout is enabled at inference to estimate predictive distributions, and sample acquisition is driven by mutual-information-based querying to prioritize epistemically informative target patches, addressing the small-sample supervision challenge emphasized in remote-sensing deep learning. This design turns uncertainty into an operational annotation policy rather than a passive diagnostic output. Experimental results show that the framework consistently outperforms deterministic counterparts and strong active-learning baselines in spectrally complex mine scenes, while approaching the fully supervised upper bound with only a small fraction of local labels. The approach is especially effective in shadowed benches and fault-adjacent slopes, supporting trustworthy deployment for geohazard monitoring and disaster-relevant slope safety workflows; extension to multi-modal constraints (e.g., SAR or elevation) is discussed as future work.
Förderung
- Key Program of National Natural Science Foundation of China
Zitieren
APA
Li, H., Hu, X., Ren, F., Lan, Z., & Cai, S. (2026). Uncertainty-Aware Label-Efficient Landslide Segmentation in Open-Pit Mines via Transformer Transfer Learning and Active Learning. Remote Sensing, 18(11), 1774. https://doi.org/10.3390/rs18111774
Vancouver
Li H, Hu X, Ren F, Lan Z, Cai S. Uncertainty-Aware Label-Efficient Landslide Segmentation in Open-Pit Mines via Transformer Transfer Learning and Active Learning. Remote Sensing. 2026;18(11):1774. doi:10.3390/rs18111774
BibTeX
@article{Li2026,
author = {Li, Haiying and Hu, Xin and Ren, Fengyu and Lan, Zhou and Cai, Sheng},
title = {Uncertainty-Aware Label-Efficient Landslide Segmentation in Open-Pit Mines via Transformer Transfer Learning and Active Learning},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {11},
pages = {1774},
doi = {10.3390/rs18111774}
}
EUVIMED