Efficient Evaluation-Time Uncertainty Estimation by Improved DistillationEfficient Evaluation-Time Uncertainty Estimation by Improved DistillationEnglesson, Erik and Azizpour, Hossein2019

Paper summarydavidstutzEnglesson and Azizpour propose an adapted knowledge distillation version to improve confidence calibration on out-of-distribution examples including adversarial examples. In contrast to vanilla distillation, they make the following changes: First, high capacity student networks are used, for example, by increasing depth or with. Then, the target distribution is “sharpened” using the true label by reducing the distributions overall entropy. Finally, for wrong predictions of the teacher model, they propose an alternative distribution with maximum mass on the correct class, while not losing the information provided on the incorrect label.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

Englesson and Azizpour propose an adapted knowledge distillation version to improve confidence calibration on out-of-distribution examples including adversarial examples. In contrast to vanilla distillation, they make the following changes: First, high capacity student networks are used, for example, by increasing depth or with. Then, the target distribution is “sharpened” using the true label by reducing the distributions overall entropy. Finally, for wrong predictions of the teacher model, they propose an alternative distribution with maximum mass on the correct class, while not losing the information provided on the incorrect label.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).