Evaluates Mask R-CNN with multiple feature extractors on the 2015 MICCAI polyp dataset, reports peak scores of 72.59% recall and 70.42% Dice, claims SOTA segmentation, and concludes data quality can matter as much as network depth.
com- parative validation of polyp detection methods in video colonoscopy: results from the miccai 2015 endoscopic vision challenge,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?
Evaluates Mask R-CNN with multiple feature extractors on the 2015 MICCAI polyp dataset, reports peak scores of 72.59% recall and 70.42% Dice, claims SOTA segmentation, and concludes data quality can matter as much as network depth.