Abstract

Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities. In this project, we develop new approaches to calibrate classifier outputs (including neural networks) and take steps towards theoretically understanding and improving existing calibration methods.

Publications

Post-hoc Calibration of Neural Networks.
Amir Rahimi, Kartik Gupta, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, and Richard Hartley.
arxiv:2006.12807, June 2020.
[pdf] [arxiv] [bib]

Calibration of Neural Networks using Splines.
Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, and Richard Hartley.
International Conference on Learning Representations (ICLR), May 2021.
[pdf] [arxiv] [bib]