Misclassification risk and uncertainty quantification in deep classifiers

Name: Misclassification risk and uncertainty quantification in deep classifiers
Author: Şensoy, Murat, Saleki, Maryam, Julier, S., Aydoğan, Reyhan, Reid, J.

İsim	Misclassification risk and uncertainty quantification in deep classifiers
Yazar	Şensoy, Murat, Saleki, Maryam, Julier, S., Aydoğan, Reyhan, Reid, J.
Basım Tarihi:	2021
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-073814266-1
Kayıt Numarası	a10c90b0-a05c-4cb1-925d-d4f245c96b8d
Lokasyon	Computer Science
Tarih	2021
Notlar	United States Department of Defense US Army Research Laboratory (ARL)
Örnek Metin	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.
DOI	10.1109/WACV48630.2021.00253

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Misclassification risk and uncertainty quantification in deep classifiers

Yazar Şensoy, Murat, Saleki, Maryam, Julier, S., Aydoğan, Reyhan, Reid, J.

Basım Tarihi 2021

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-073814266-1

Kayıt Numarası a10c90b0-a05c-4cb1-925d-d4f245c96b8d

Lokasyon Computer Science

Tarih 2021

Notlar United States Department of Defense US Army Research Laboratory (ARL)

Örnek Metin 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.

DOI 10.1109/WACV48630.2021.00253