A frozen DINOv3 ViT-L/16 with AnyUp upsampling and lightweight CenterNet heads achieves 0.893 F1 and 1.41 mm localization error on arrow punctures using 48 training images.
DINOv2: Learning robust vi- sual features without supervision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Frozen Vision Transformers for Dense Prediction on Small Datasets: A Case Study in Arrow Localization
A frozen DINOv3 ViT-L/16 with AnyUp upsampling and lightweight CenterNet heads achieves 0.893 F1 and 1.41 mm localization error on arrow punctures using 48 training images.