COMPARISON OF UNCERTAINTY QUANTIFICATION METHODS FOR CNN-BASED REGRESSION
Abstract. The evaluation of reliability is not only of high importance for safety-critical deep learning applications but for object pose estimation as well. The uncertainty of the result is one way to express its reliability. In order to better understand existing uncertainty quantification (UQ) methods and their performance on image-based regression tasks, we use a small CNN and various scenarios to evaluate the estimated uncertainties. The evaluation is done on different simplistic synthetic datasets, consisting of gray-scale images of squares on a darker background. We train the CNN to predict the square center position of the square in the image. We compare how different UQ methods perform under dataset shift, rotation, occlusion, noise changes in the images.
- Location
-
Deutsche Nationalbibliothek Frankfurt am Main
- Extent
-
Online-Ressource
- Language
-
Englisch
- Bibliographic citation
-
COMPARISON OF UNCERTAINTY QUANTIFICATION METHODS FOR CNN-BASED REGRESSION ; volume:XLIII-B2-2022 ; year:2022 ; pages:721-728 ; extent:8
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ; XLIII-B2-2022 (2022), 721-728 (gesamt 8)
- Creator
-
Wursthorn, K.
Hillemann, M.
Ulrich, M.
- DOI
-
10.5194/isprs-archives-XLIII-B2-2022-721-2022
- URN
-
urn:nbn:de:101:1-2022060206090498593820
- Rights
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Last update
-
15.08.2025, 7:25 AM CEST
Data provider
This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Associated
- Wursthorn, K.
- Hillemann, M.
- Ulrich, M.
Other Objects (12)
Multifaceted uncertainty quantification
Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks
Evaluation of a sampling approach for computationally efficient uncertainty quantification in regression learning models
Contour Method with Uncertainty Quantification: A Robust and Optimised Framework via Gaussian Process Regression
A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling
Uncertainty Quantification of Reactivity Scales **
Uncertainty Quantification in Reacting Flows
Uncertainty quantification and Heston model
Similarity-based pairing improves efficiency of siamese neural networks for regression tasks and uncertainty quantification
CNN
Uncertain of uncertainties? A comparison of uncertainty quantification metrics for chemical data sets
Uncertainty quantification with advanced simulation methods
Multifaceted uncertainty quantification
Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks
Evaluation of a sampling approach for computationally efficient uncertainty quantification in regression learning models
Contour Method with Uncertainty Quantification: A Robust and Optimised Framework via Gaussian Process Regression
A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling
Uncertainty Quantification of Reactivity Scales **
Uncertainty Quantification in Reacting Flows
Uncertainty quantification and Heston model
Similarity-based pairing improves efficiency of siamese neural networks for regression tasks and uncertainty quantification
CNN
Uncertain of uncertainties? A comparison of uncertainty quantification metrics for chemical data sets
Uncertainty quantification with advanced simulation methods
Multifaceted uncertainty quantification
Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks
Evaluation of a sampling approach for computationally efficient uncertainty quantification in regression learning models
Contour Method with Uncertainty Quantification: A Robust and Optimised Framework via Gaussian Process Regression
A hybrid framework for improving uncertainty quantification in deep learning-based QSAR regression modeling
Uncertainty Quantification of Reactivity Scales **
Uncertainty Quantification in Reacting Flows
Uncertainty quantification and Heston model
Similarity-based pairing improves efficiency of siamese neural networks for regression tasks and uncertainty quantification
CNN
Uncertain of uncertainties? A comparison of uncertainty quantification metrics for chemical data sets