Dropout Distillation for Efficiently Estimating Model Confidence

Dropout Distillation for Efficiently Estimating Model Confidence

27 September 2018

Alex Bewley

Papers citing "Dropout Distillation for Efficiently Estimating Model Confidence"

7 / 7 papers shown

Title
Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimation S. Landgraf Markus Hillemann Theodor Kapler Markus Ulrich UQCV 39 8 0 16 Feb 2024
Robust Models are less Over-Confident Julia Grabinski Paul Gavrikov J. Keuper M. Keuper AAML 36 24 0 12 Oct 2022
Confidence-Aware Learning for Deep Neural Networks J. Moon Jihyo Kim Younghak Shin Sangheum Hwang UQCV 28 144 0 03 Jul 2020
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation Erik Englesson Hossein Azizpour UQCV 19 8 0 12 Jun 2019
Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection Dimity Miller Feras Dayoub Michael Milford Niko Sünderhauf 23 105 0 17 Sep 2018
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,695 0 05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 287 9,167 0 06 Jun 2015