Benchmarking the Domain Gap measures how model rankings change across video capsule endoscopy datasets and shared-label targets.
unassessed
| Category | domain |
|---|---|
| Subcategory | video capsule endoscopy |
| Metric | classification performance and ranking stability |
| Direction | higher_is_better |
| Unit | score |
| Publisher | Dan Hanson and Debesh Jha |
The study evaluates image-classification backbones trained on Kvasir-Capsule and tested across Kvasir-Capsule, Capsule Vision 2024, and a shared-label subset of Galar. It measures cross-target ranking stability under domain shift.
Supervised image classification on endoscopy frames or clips with shared-label evaluation.
No model card in ModelSpec reports this benchmark yet.