A ViT-base model pretrained on ImageNet-21k outperforms a ResNet50 baseline on kidney stone subtype classification, but the advantage may come from pretraining scale, not the transformer architecture.
survey results practice committee of the afu lithiasis completed in 2011
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vision Transformers for Kidney Stone Image Classification: A Comparative Study with CNNs
A ViT-base model pretrained on ImageNet-21k outperforms a ResNet50 baseline on kidney stone subtype classification, but the advantage may come from pretraining scale, not the transformer architecture.