Quantifying Uncertainty from Different Sources in Deep Neural Networks for Image Classification

11/17/2020
by   Aria Khoshsirat, et al.
17

Quantifying uncertainty in a model's predictions is important as it enables, for example, the safety of an AI system to be increased by acting on the model's output in an informed manner. We cannot expect a system to be 100 accurate or perfect at its task, however, we can equip the system with some tools to inform us if it is not certain about a prediction. This way, a second check can be performed, or the task can be passed to a human specialist. This is crucial for applications where the cost of an error is high, such as in autonomous vehicle control, medical image analysis, financial estimations or legal fields. Deep Neural Networks are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in DNNs is a challenging and yet on-going problem. Although there have been many efforts to equip NNs with tools to estimate uncertainty, such as Monte Carlo Dropout, most of the previous methods only focus on one of the three types of model, data or distributional uncertainty. In this paper we propose a complete framework to capture and quantify all of these three types of uncertainties in DNNs for image classification. This framework includes an ensemble of CNNs for model uncertainty, a supervised reconstruction auto-encoder to capture distributional uncertainty and using the output of activation functions in the last layer of the network, to capture data uncertainty. Finally we demonstrate the efficiency of our method on popular image datasets for classification.

READ FULL TEXT

page 9

page 10

page 11

page 12

page 15

research
06/01/2021

Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning

Deep neural networks are increasingly being used for the analysis of med...
research
06/04/2022

Quantifying and Using System Uncertainty in UAV Navigation

As autonomous systems increasingly rely on Deep Neural Networks (DNN) to...
research
05/20/2022

A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networks

Graph Neural Networks (GNN) provide a powerful framework that elegantly ...
research
02/28/2018

Predictive Uncertainty Estimation via Prior Networks

Estimating uncertainty is important to improving the safety of AI system...
research
01/20/2022

SoftDropConnect (SDC) – Effective and Efficient Quantification of the Network Uncertainty in Deep MR Image Analysis

Recently, deep learning has achieved remarkable successes in medical ima...
research
04/20/2023

Multidimensional Uncertainty Quantification for Deep Neural Networks

Deep neural networks (DNNs) have received tremendous attention and achie...
research
07/14/2020

An Uncertainty-based Human-in-the-loop System for Industrial Tool Wear Analysis

Convolutional neural networks have shown to achieve superior performance...

Please sign up or login with your details

Forgot password? Click here to reset