Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?

08/26/2019
by   Martin Mundt, et al.
0

We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition. While the former alone does not seem to be enough to overcome this challenge, we demonstrate that uncertainty goes hand in hand with the latter method. This seems to be particularly reflected in a generative model approach, where we show that posterior based open set recognition outperforms discriminative models and predictive uncertainty based outlier rejection, raising the question of whether classifiers need to be generative in order to know what they have not seen.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/02/2021

Why Calibration Error is Wrong Given Model Uncertainty: Using Posterior Predictive Checks with Deep Learning

Within the last few years, there has been a move towards using statistic...
research
06/07/2020

Uncertainty-Aware Deep Classifiers using Generative Models

Deep neural networks are often ignorant about what they do not know and ...
research
12/05/2020

Quantifying Aleatoric and Epistemic Uncertainty Using Density Estimation in Latent Space

The distribution of a neural network's latent representations has been s...
research
05/15/2022

Evaluating Uncertainty Calibration for Open-Set Recognition

Despite achieving enormous success in predictive accuracy for visual cla...
research
07/11/2023

Random-Set Convolutional Neural Network (RS-CNN) for Epistemic Deep Learning

Machine learning is increasingly deployed in safety-critical domains whe...
research
05/30/2019

Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections

Quantifying and measuring uncertainty in deep neural networks, despite r...
research
12/22/2020

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Humor recognition has been widely studied as a text classification probl...

Please sign up or login with your details

Forgot password? Click here to reset