A CNN with attention blocks reports 99.8% accuracy on a single-hospital colposcopy dataset, but image-level splitting likely mixes images from the same patient in training and test sets, and the paper's own confusion matrix contradicts its reported accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Explainable Attention Model for Cervical Precancer Risk Classification using Colposcopic Images
A CNN with attention blocks reports 99.8% accuracy on a single-hospital colposcopy dataset, but image-level splitting likely mixes images from the same patient in training and test sets, and the paper's own confusion matrix contradicts its reported accuracy.