UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Misclassification Risk and Uncertainty Quantification in Deep Classifiers

Sensoy, M; Saleki, M; Julier, S; Aydogan, R; Reid, J; (2021) Misclassification Risk and Uncertainty Quantification in Deep Classifiers. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV) 2021. (pp. pp. 2483-2491). Institute of Electrical and Electronics Engineers (IEEE) Green open access

[thumbnail of Sensoy_Misclassification_Risk_and_Uncertainty_Quantification_in_Deep_Classifiers_WACV_2021_paper.pdf]
Preview
Text
Sensoy_Misclassification_Risk_and_Uncertainty_Quantification_in_Deep_Classifiers_WACV_2021_paper.pdf - Published Version

Download (9MB) | Preview

Abstract

In this paper, we propose risk-calibrated evidential deep classifiers to reduce the costs associated with classification errors. We use two main approaches. The first is to develop methods to quantify the uncertainty of a classifier’s predictions and reduce the likelihood of acting on erroneous predictions. The second is a novel way to train the classifier such that erroneous classifications are biased towards less risky categories. We combine these two approaches in a principled way. While doing this, we extend evidential deep learning with pignistic probabilities, which are used to quantify uncertainty of classification predictions and model rational decision making under uncertainty.We evaluate the performance of our approach on several image classification tasks. We demonstrate that our approach allows to (i) incorporate misclassification cost while training deep classifiers, (ii) accurately quantify the uncertainty of classification predictions, and (iii) simultaneously learn how to make classification decisions to minimize expected cost of classification errors.

Type: Proceedings paper
Title: Misclassification Risk and Uncertainty Quantification in Deep Classifiers
Event: The Winter Conference on Applications of Computer Vision (WACV) 2021
ISBN-13: 978-1-6654-0477-8
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/WACV48630.2021.00253
Publisher version: https://doi.org/10.1109/WACV48630.2021
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Training, Deep learning, Computer vision, Uncertainty, Conferences, Decision making, Predictive models
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10132169
Downloads since deposit
75Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item