Evidential Uncertainty Quantification: A Variance-Based Perspective
Authors:
- 3 January 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2121-2130
Abstract
Uncertainty quantification of deep neural networks has become an active field of research and plays a crucial role in various downstream tasks such as active learning. Recent advances in evidential deep learning shed light on the direct quantification of aleatoric and epistemic uncertainties with a single forward pass of the model. Most traditional approaches adopt an entropy-based method to derive evidential uncertainty in classification, quantifying uncertainty at the sample level. However, the variance-based method that has been widely applied in regression problems is seldom used in the classification setting. In this work, we adapt the variance-based approach from regression to classification, quantifying classification uncertainty at the class level. The variance decomposition technique in regression is extended to class covariance decomposition in classification based on the law of total covariance, and the class correlation is also derived from the covariance. Experiments on cross-domain datasets are conducted to illustrate that the variance-based approach not only results in similar accuracy as the entropy-based one in active domain adaptation but also brings information about class-wise uncertainties as well as between-class correlations. The code is available at https://github.com/KerryDRX/EvidentialADA. This alternative means of evidential uncertainty quantification will give researchers more options when class uncertainties and correlations are important in their applications.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- A survey of uncertainty in deep neural networksArtificial Intelligence Review, 2023
- Region-based evidential deep learning to quantify uncertainty and improve robustness of brain tumor segmentationNeural Computing and Applications, 2022
- Uncertainty estimation for stereo matching based on evidential deep learningPattern Recognition, 2022
- DEAL: Deep Evidential Active Learning for Image Classification2021
- Evidential Deep Learning for Guided Molecular Property Prediction and DiscoveryACS Central Science, 2021
- Density Estimation in Representation Space to Predict Model Uncertainty2020
- Bayesian QuickNAT: Model uncertainty in deep whole-brain segmentation for structure-wise quality controlNeuroImage, 2019
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009
- Multi-class active learning for image classification2009