Trust your neighbours: Penalty-based constraints for model calibration

Trust your neighbours: Penalty-based constraints for model calibration

11 March 2023

Balamurali Murugesan

Ismail Ben Ayed

Jose Dolz

Papers citing "Trust your neighbours: Penalty-based constraints for model calibration"

4 / 4 papers shown

Title
Do not trust what you trust: Miscalibration in Semi-supervised Learning Shambhavi Mishra Balamurali Murugesan Ismail Ben Ayed M. Pedersoli Jose Dolz 48 2 0 22 Mar 2024
Class and Region-Adaptive Constraints for Network Calibration Balamurali Murugesan Julio Silva-Rodríguez Ismail Ben Ayed Jose Dolz 36 1 0 19 Mar 2024
Boundary-weighted logit consistency improves calibration of segmentation networks Neerav Karani Neel Dey Polina Golland 19 3 0 16 Jul 2023
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,138 0 06 Jun 2015