Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks

neural information processing systems, 2020.

Cited by: 1|Bibtex|Views42
Other Links: arxiv.org|academic.microsoft.com

Abstract:

Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration function that transforms the output of the original network into calibrated confidence scores while maintaining the network's accuracy. However, previous post-hoc ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments