mlsanityData to 7 Oct 2026

Benchmarking the Domain Gap: Model Selection Instability Under Domain Shift in Video Capsule Endoscopy

arXiv 2607.22736 ↗First posted 22 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Video capsule endoscopy (VCE) classification is typically evaluated within a single dataset, yet clinical deployment demands robustness across acquisition sources, labeling policies, and patient populations. We examine this gap using Kvasir-Capsule, Capsule Vision 2024 (CV2024), and a shared-label subset of Galar. We fine-tune a suite of general-domain pretrained backbones on the official Kvasir-Capsule folds under a standardized protocol and evaluate the same checkpoints on two non-source targets within a documented shared-label decision space. We find that the predictive value of in-domain ranking is target-dependent: Kvasir-Capsule ranking aligns more closely with Galar than with CV2024, while the two non-source targets agree only weakly. Consequently, the strongest in-domain backbone leads on one target yet falls to mid-pack on the other, and no single evaluation target reliably predicts the others. A second CV2024-trained configuration set reproduces this target-dependent instability. We conclude that capsule endoscopy model selection should report cross-target ranking stability rather than peak single-dataset performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 22 Jul 2026.

Builds on

19 of 33 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2022A ConvNet for the 2020scited by 3,545
  8. 2019Natural Adversarial Examplescited by 1,401
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  10. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  11. 2020In Search of Lost Domain Generalizationcited by 1,042
  12. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
7 more
  1. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
  2. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  3. 2022Focal Modulation Networkscited by 186
  4. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  5. 2022MetaFormer Baselines for Visioncited by 131
  6. 2020On the limits of cross-domain generalization in automated X-ray predictioncited by 61
  7. 2024Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopycited by 16

Built on by

Not cited yet.