Code of our method MbLS (Margin-based Label Smoothing) for network calibration. To Appear at CVPR 2022. Paper : https://arxiv.org/abs/2111.15430

Code for our method CALS (Class Adaptive Label Smoothing) for network calibration. To Appear at CVPR 2023. Paper: https://arxiv.org/abs/2211.15088

Code for the paper "Calibrating Deep Neural Networks using Focal Loss"

Model-agnostic posthoc calibration without distributional assumptions

This is the implementation of our CVPR'23 paper On the Pitfall of Mixup for Uncertainty Calibration. In the paper, we conduct a series of empirical studies showing the calibration issue of Mixup, a…

[ICLR'23] ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure