Answers are grounded in this paper and cite their sources.
We adapted two explainability methods commonly used in image classification, KernelSHAP and Grad-CAM, to colonoscopy video classification.We evaluated their plausibility by measuring how well their approximation of EndoFMLV’s visual focus for polyp class predictions aligned with the visible polyp region. Both methods showed low plausibility, and plausibility alone could not reveal model faults reliably.
No takes yet. Share an insight, caveat, or question.
Opolka et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: