With recent developments, the performance of automotive radar has improved significantly.
The next generation of 4D radar can achieve imaging capability in the form of high …

Over the last decade, neural networks have reached almost every field of science and
become a crucial part of various real world applications. Due to the increasing spread …

The point estimates of ReLU classification networks—arguably the most widely used neural
network architecture—have been shown to yield arbitrarily high confidence far away from …

This paper studies the problem of post-hoc calibration of machine learning classifiers. We
introduce the following desiderata for uncertainty calibration:(a) accuracy-preserving,(b) …

Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …

This paper provides both an introduction to and a detailed overview of the principles and
practice of classifier calibration. A well-calibrated classifier correctly quantifies the level of …

Optimal decision making requires that classifiers produce uncertainty estimates consistent
with their empirical accuracy. However, deep neural networks are often under-or over …

With model trustworthiness being crucial for sensitive real-world applications, practitioners
are putting more and more focus on improving the uncertainty calibration of deep neural …

Calibrated probabilistic classifiers are models whose predicted probabilities can directly be
interpreted as uncertainty estimates. It has been shown recently that deep neural networks …

How to estimate the uncertainty of a given model is a crucial problem. Current calibration
techniques treat different classes equally and thus implicitly assume that the distribution of …