mlsanityData to 14 Oct 2026

Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty

arXiv 2404.10980 ↗First posted 17 Apr 2024cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 26 of its 54 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

26 of 54 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  6. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  7. 2020Classification with Valid and Adaptive Coveragecited by 396
  8. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  9. 2019Human uncertainty makes classification more robustcited by 235
  10. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  11. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  12. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
14 more
  1. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  2. 2020Provably Consistent Partial-Label Learningcited by 92
  3. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  4. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 66
  5. 2021Instance-Dependent Partial Label Learningcited by 49
  6. 2022Eliciting and Learning with Soft Labels from Every Annotatorcited by 43
  7. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  8. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 31
  9. 2019Uncertainty on Asynchronous Time Event Predictioncited by 27
  10. 2023Dirichlet-based Uncertainty Calibration for Active Domain Adaptationcited by 24
  11. 2023Long-Tailed Partial Label Learning via Dynamic Rebalancingcited by 22
  12. 2016PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognitioncited by 18
  13. 2021An evidential classifier based on Dempster-Shafer theory and deep learningcited by 18
  14. 2023Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularizationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 5.

11 papers.

  1. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  2. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  3. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 14
  4. 2024Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Functioncited by 2
  5. 2025Fairness-Aware Multi-view Evidential Learning with Adaptive Priorcited by 1
  6. 2026Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learningcited by 1
  7. 2026PriorNet: Prior-Guided Engagement Estimation from Face Videocited by 1
  8. 2025Detecting underdetermination in parameterized quantum circuitscited by 0
  9. 2026Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classificationcited by 0
  10. 2026H2EDL: Hyper Evidential Deep Learning for Hierarchical Classificationcited by 0
  11. 2026Evidential Multimodal Transformers with Dempster-Shafer Fusion for Emotion Recognitioncited by 0