DeepAI AI Chat
Log In Sign Up

Decomposing Representations for Deterministic Uncertainty Estimation

by   Haiwen Huang, et al.
University of Oxford

Uncertainty estimation is a key component in any deployed machine learning system. One way to evaluate uncertainty estimation is using "out-of-distribution" (OoD) detection, that is, distinguishing between the training data distribution and an unseen different data distribution using uncertainty. In this work, we show that current feature density based uncertainty estimators cannot perform well consistently across different OoD detection settings. To solve this, we propose to decompose the learned representations and integrate the uncertainties estimated on them separately. Through experiments, we demonstrate that we can greatly improve the performance and the interpretability of the uncertainty estimation.


page 1

page 2

page 3

page 4


Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

Among existing uncertainty estimation approaches, Dirichlet Prior Networ...

EnSolver: Uncertainty-Aware CAPTCHA Solver Using Deep Ensembles

The popularity of text-based CAPTCHA as a security mechanism to protect ...

Training, Architecture, and Prior for Deterministic Uncertainty Methods

Accurate and efficient uncertainty estimation is crucial to build reliab...

Accurate Uncertainty Estimation and Decomposition in Ensemble Learning

Ensemble learning is a standard approach to building machine learning sy...

Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap

Monitoring machine learning models once they are deployed is challenging...

Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations

Our goal is to evaluate the accuracy of a black-box classification model...

Which models are innately best at uncertainty estimation?

Deep neural networks must be equipped with an uncertainty estimation mec...