Fine-tuned SAM generalizes much better than U-Net variants to unseen kidney stone image distributions, with out-of-distribution IoU margins of up to 23 percentage points.
On the generalization capabilities of fsl methods through domain adaptation: a case study in endoscopic kidney stone image classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Assessing the generalization performance of SAM for ureteroscopy scene understanding
Fine-tuned SAM generalizes much better than U-Net variants to unseen kidney stone image distributions, with out-of-distribution IoU margins of up to 23 percentage points.