Adding a regression constraint to a cross-entropy classifier improves cervical cell severity classification on Herlev from 70.1% to 74.5% accuracy and produces nucleus-focused attributions.
Medical Ima- ging 2015 : Computer-Aided Diagnosis, 2015
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Regression Constraint for an Explainable Cervical Cancer Classifier
Adding a regression constraint to a cross-entropy classifier improves cervical cell severity classification on Herlev from 70.1% to 74.5% accuracy and produces nucleus-focused attributions.