Viet-Anh on Software Logo

What is: Confidence Calibration with an Auxiliary Class)?

SourceCalibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Confidence Calibration with an Auxiliary Class, or CCAC, is a post-hoc confidence calibration method for DNN classifiers on OOD datasets. The key feature of CCAC is an auxiliary class in the calibration model which separates mis-classified samples from correctly classified ones, thus effectively mitigating the target DNN’s being confidently wrong. It also reduces the number of free parameters in CCAC to reduce free parameters and facilitate transfer to a new unseen dataset.