2020
EGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis
ECCV 2020poster
Today's computer-aided diagnosis (CAD) model is still far from the clinical practice of glaucoma detection, mainly due to the training bias originating from 1) the normal-abnormal class imbalance and 2) the rare but significant hard samples in fundus images. However, debiasing in CAD is not trivial…