DINOv3 pretraining yields no frozen advantage and underperforms ImageNet on X-ray but improves convergence and final performance after full finetuning on RGB industrial inspection tasks.
A comprehensive sur- vey for real-world industrial surface defect detection: Chal- lenges, approaches, and prospects.Journal of Manufacturing Systems, 84:152–172
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Rethinking Transfer Learning for Industrial Inspection: DINOv3 vs. ImageNet Pretraining Across RGB and X-ray Tasks
DINOv3 pretraining yields no frozen advantage and underperforms ImageNet on X-ray but improves convergence and final performance after full finetuning on RGB industrial inspection tasks.