Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty

2024-04-17 · Changbin Li, Kangshuo Li, Yuzhe Ou, Lance M. Kaplan, Audun Jøsang, Jin-Hee Cho, Dong Hyun Jeong, Feng Chen

Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them. This scenario necessitates the use of composite class labels. In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty due to composite class labels in training data in the context of the belief theory called Subjective Logic (SL). By placing a grouped Dirichlet distribution on the class probabilities, we treat predictions of a neural network as parameters of hyper-subjective opinions and learn the network that collects both single and composite evidence leading to these hyper-opinions by a deterministic DNN from data. We introduce a new uncertainty type called vagueness originally designed for hyper-opinions in SL to quantify composite classification uncertainty for DNNs. Our results demonstrate that HENN outperforms its state-of-the-art counterparts based on four image datasets. The code and datasets are available at: https://github.com/Hugo101/HyperEvidentialNN.

📄 PDF Abstract BibTeX arXiv:2404.10980

Code (1)

hugo101/hyperevidentialnn 공식 구현 pytorch

Tasks

Deep LearningMulti-class Classification

Evidential Uncertainty Quantification: A Variance-Based Perspective

2023-11-19 · Ruxiao Duan, Brian Caffo, Harrison X. Bai, Haris I. Sair 외

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 lig…

Active Learning Classification Domain Adaptation regression+1

Bayesian Evidential Deep Learning with PAC Regularization

2019-06-03 · pproximateinference AABI Symposium 2021 1 · Manuel Haussmann, Sebastian Gerwinn, Melih Kandemir

We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has been impactful as being both simple to i…

Deep Learning Uncertainty Quantification

Uncertainty Estimation via Hyperspherical Confidence Mapping

2026-05-07 · Eunseo Choi, Ho-Yeon Kim, Jaewon Lee, Taeyong jo 외 arxiv

Quantifying uncertainty in neural network predictions is essential for high-stakes domains such as autonomous driving, healthcare, and manufacturing. While existing approaches often depend on costly sampling or restricti…

Autonomous Driving

Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

2025-01-10 · Ayush Khot, Xiwei Wang, Avik Roy, Volodymyr Kindratenko 외

Current methods commonly used for uncertainty quantification (UQ) in deep learning (DL) models utilize Bayesian methods which are computationally expensive and time-consuming. In this paper, we provide a detailed study o…

Anomaly Detection Benchmarking Out-of-Distribution Detection Uncertainty Quantification

Uncertainty Estimation by Density Aware Evidential Deep Learning

2024-09-13 · Taeseong Yoon, Heeyoung Kim

Evidential deep learning (EDL) has shown remarkable success in uncertainty estimation. However, there is still room for improvement, particularly in out-of-distribution (OOD) detection and classification tasks. The limit…

Classification Deep Learning Out of Distribution (OOD) Detection