Confidence Calibration with an Auxiliary Class)

Introduced by Shao et al. in Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets

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.

Source: Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets

Read Paper

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Model Predictive Control	1	50.00%
Reinforcement Learning (RL)	1	50.00%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Confidence Calibration