A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration

1 code implementation • CVPR 2022 • Ramya Hebbalaguppe, Jatin Prakash, Neelabh Madan, Chetan Arora

We show that training with MDCA leads to better-calibrated models in terms of Expected Calibration Error ( ECE ), and Static Calibration Error ( SCE ) on image classification, and segmentation tasks.

Image Classification Semantic Segmentation