probability calibration

For semantic segmentation, label probabilities are often uncalibrated as they are typically only the by-product of a segmentation task. Intersection over Union (IoU) and Dice score are often used as criteria for segmentation success, while metrics …

Deep segmentation networks typically create their outputs via a softmax. Hence, the assignment appears to be probabilistic. However, it has been shown in literatute that interpreting these softmax outputs as label probabilities is not reliable and that they tend to be overly confident.