Adapting Vision Foundation Models with Synthetic Data for Open-Pit Mining Crack Segmentation
Machine Learning and Knowledge Extraction · 16.11.2026 · 8 (11) · 380
DOI: 10.3390/make8110380 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 16.11.2026. Verfasst von Rohan Le Roux und 3 weiteren Autor:innen. Die Arbeit nennt 101 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Automatic crack segmentation in open-pit mining is constrained by the scarcity of representative, labeled datasets. Vision foundation models (VFMs) offer transferable visual representations, but their training-free performance on mining imagery and the benefits of synthetic-only adaptation remain insufficiently established. This study evaluates training-free VFM pipelines and investigates whether synthetic supervision improves their transfer to real-world crack imagery. SynthMineCrack is introduced as a diverse open-pit mining crack dataset, supporting model training and hyperparameter selection without real imagery or manual annotations. SAM 3 is adapted using low-rank adaptation (LoRA), layer normalization (LN) tuning, and adapters, individually and jointly, and compared with task-specific models trained on the same synthetic data. Evaluation on both in- and out-of-domain datasets shows that SAM 3 achieves the strongest training-free performance, while joint adaptation of all three operators improves intersection-over-union (IoU) on the mining evaluation dataset by 18.25 percentage points (pp). This configuration achieves a mean IoU of 69.39% across the five datasets, exceeding SegFormer, the strongest task-specific model, by 10.77 pp. Diagnostic analyses associate these gains with more complete crack recovery while the pretrained visual representation remains largely preserved. This configuration updates only 0.326% of the instantiated model’s parameter count and incurs little additional inference overhead. Together, these findings support synthetic-only adaptation as a practical means of improving SAM 3 for real-world crack segmentation while retaining inference requirements close to those of the base model.
Zitieren
APA
Roux, R. L., Khaksar, S., Sepehri, M., & Murray, I. (2026). Adapting Vision Foundation Models with Synthetic Data for Open-Pit Mining Crack Segmentation. Machine Learning and Knowledge Extraction, 8(11), 380. https://doi.org/10.3390/make8110380
Vancouver
Roux RL, Khaksar S, Sepehri M, Murray I. Adapting Vision Foundation Models with Synthetic Data for Open-Pit Mining Crack Segmentation. Machine Learning and Knowledge Extraction. 2026;8(11):380. doi:10.3390/make8110380
BibTeX
@article{Roux2026,
author = {Roux, Rohan Le and Khaksar, Siavash and Sepehri, Mohammadali and Murray, Iain},
title = {Adapting Vision Foundation Models with Synthetic Data for Open-Pit Mining Crack Segmentation},
journal = {Machine Learning and Knowledge Extraction},
year = {2026},
volume = {8},
number = {11},
pages = {380},
doi = {10.3390/make8110380}
}
EUVIMED