Revisiting the Calibration of Modern Neural Networks

06/15/2021 ∙ by Matthias Minderer, et al. ∙ 18

Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networks have been reported, suggesting a trend that newer, more accurate models produce poorly calibrated predictions. Here, we revisit this question for recent state-of-the-art image classification models. We systematically relate model calibration and accuracy, and find that the most recent models, notably those not using convolutions, are among the best calibrated. Trends observed in prior model generations, such as decay of calibration with distribution shift or model size, are less pronounced in recent architectures. We also show that model size and amount of pretraining do not fully explain these differences, suggesting that architecture is a major determinant of calibration properties.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 25

page 26

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.