PEP: Parameter Ensembling by Perturbation

PEP: Parameter Ensembling by Perturbation

24 October 2020

Alireza Mehrtash

Purang Abolmaesumi

Demian Wassermann

Papers citing "PEP: Parameter Ensembling by Perturbation"

7 / 7 papers shown

Title
Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective Xueqiong Yuan Jipeng Li E. Kuruoglu UQCV BDL 45 0 0 21 Jan 2025
Instance-Aware Observer Network for Out-of-Distribution Object Segmentation Victor Besnier Andrei Bursuc David Picard Alexandre Briot 39 1 0 18 Jul 2022
Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation Victor Besnier Andrei Bursuc David Picard Alexandre Briot UQCV 24 48 0 03 Aug 2021
Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness Ahmadreza Jeddi M. Shafiee Michelle Karg C. Scharfenberger A. Wong OOD AAML 58 63 0 02 Mar 2020
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam Mohammad Emtiyaz Khan Didrik Nielsen Voot Tangkaratt Wu Lin Y. Gal Akash Srivastava ODL 74 266 0 13 Jun 2018
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,661 0 05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,138 0 06 Jun 2015