Code for calibration of trained segmentation models using platt scaling, fine tuning and simple convolutional auxiliary networks
Neural networks for automated image segmentation are typically trained to achieve maximum accuracy, while less attention has been given to the calibration of their confidence scores. However, well-calibrated confidence scores provide valuable information towards the user. We investigate several post hoc calibration methods that are straightforward to implement, some of which are novel, and compare them to Monte Carlo dorpout.