The Devil is in the Margin: Margin-based Label Smoothing for Network
Calibration

The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration

30 November 2021

Ismail Ben Ayed

Jose Dolz

Papers citing "The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration"

4 / 54 papers shown

Title
Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation Agostina J. Larrazabal Cesar E. Martínez Jose Dolz Enzo Ferrante 11 15 0 22 Dec 2021
Probabilistic Approach for Road-Users Detection Gledson Melotti Weihao Lu Pedro Conde Dezong Zhao A. Asvadi Nuno Gonçalves C. Premebida 19 2 0 02 Dec 2021
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 268 5,660 0 05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 249 9,134 0 06 Jun 2015