From: Ramifications of incorrect image segmentations; emphasizing on the potential effects on deep learning methods failure
AUPR-Error (%)
MNIST (MLP)
MNIST SmallConvNet
SVHN
CIFAR-10
CIFAR-100
CamVid
ConfidNet (Train set)
52.25
48.20
41.32
45.80
35.33
80.95
ConfidNet (validation set)
50.58
59.34
77.15
90.09
31.03
63.00