Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts

06/16/2020
by   Bertrand Charpentier, et al.
11

Accurate estimation of aleatoric and epistemic uncertainty is crucial to build safe and reliable systems. Traditional approaches, such as dropout and ensemble methods, estimate uncertainty by sampling probability predictions from different submodels, which leads to slow uncertainty estimation at inference time. Recent works address this drawback by directly predicting parameters of prior distributions over the probability predictions with a neural network. While this approach has demonstrated accurate uncertainty estimation, it requires defining arbitrary target parameters for in-distribution data and makes the unrealistic assumption that out-of-distribution (OOD) data is known at training time. In this work we propose the Posterior Network (PostNet), which uses Normalizing Flows to predict an individual closed-form posterior distribution over predicted probabilites for any input sample. The posterior distributions learned by PostNet accurately reflect uncertainty for in- and out-of-distribution data – without requiring access to OOD data at training time. PostNet achieves state-of-the art results in OOD detection and in uncertainty calibration under dataset shifts.

READ FULL TEXT

page 2

page 7

page 14

page 15

page 18

research
05/10/2021

Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions

Uncertainty awareness is crucial to develop reliable machine learning mo...
research
11/26/2022

Looking at the posterior: on the origin of uncertainty in neural-network classification

Bayesian inference can quantify uncertainty in the predictions of neural...
research
07/17/2020

Learning Posterior and Prior for Uncertainty Modeling in Person Re-Identification

Data uncertainty in practical person reID is ubiquitous, hence it requir...
research
11/18/2021

Locally Learned Synaptic Dropout for Complete Bayesian Inference

The Bayesian brain hypothesis postulates that the brain accurately opera...
research
05/14/2020

Constraining the Reionization History using Bayesian Normalizing Flows

The next generation 21 cm surveys open a new window onto the early stage...
research
05/12/2021

A new framework for experimental design using Bayesian Evidential Learning: the case of wellhead protection area

In this contribution, we predict the wellhead protection area (WHPA, tar...
research
04/20/2021

A Bayesian Convolutional Neural Network for Robust Galaxy Ellipticity Regression

Cosmic shear estimation is an essential scientific goal for large galaxy...

Please sign up or login with your details

Forgot password? Click here to reset