Search Results for author:
Found 2 papers, 1 papers with code
Soft Calibration Objectives for Neural Networks
When incorporated into training, these soft calibration losses achieve state-of-the-art single-model ECE across multiple datasets with less than 1% decrease in accuracy.
Mitigating Bias in Calibration Error Estimation
We find that binning-based estimators with bins of equal mass (number of instances) have lower bias than estimators with bins of equal width.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
