# An evidential classifier based on Dempster-Shafer theory and deep learning

arXiv: https://arxiv.org/abs/2103.13549 · HTML: https://mlsanity.com/paper/2103.13549/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 83 references that are in the map.
- First posted on arXiv 25 Mar 2021.

## Builds on (most cited first, 11 of 11)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [All you need is a good init](https://mlsanity.com/paper/1511.06422/) (2015)
- [Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification](https://mlsanity.com/paper/1608.04363/) (2016)
- [Multimodal Deep Learning for Robust RGB-D Object Recognition](https://mlsanity.com/paper/1507.06821/) (2015)
- [Decision-Making with Belief Functions: a Review](https://mlsanity.com/paper/1808.05322/) (2018)
- [Logistic Regression, Neural Networks and Dempster-Shafer Theory: a New Perspective](https://mlsanity.com/paper/1807.01846/) (2018)
- [Combining Multi-level Contexts of Superpixel using Convolutional Neural Networks to perform Natural Scene Labeling](https://mlsanity.com/paper/1803.05200/) (2018)

## Built on by (most cited first, 18 of 18)

- [Random-Set Neural Networks (RS-NN)](https://mlsanity.com/paper/2307.05772/) (2023)
- [Epistemic Deep Learning](https://mlsanity.com/paper/2206.07609/) (2022)
- [Lymphoma segmentation from 3D PET-CT images using a deep evidential network](https://mlsanity.com/paper/2201.13078/) (2022)
- [Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty](https://mlsanity.com/paper/2404.10980/) (2024)
- [A Unified Evaluation Framework for Epistemic Predictions](https://mlsanity.com/paper/2501.16912/) (2025)
- [Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization](https://mlsanity.com/paper/2412.19418/) (2024)
- [Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'](https://mlsanity.com/paper/2505.04950/) (2025)
- [A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning](https://mlsanity.com/paper/2206.05675/) (2022)
- [An Evidential Neural Network Model for Regression Based on Random Fuzzy Numbers](https://mlsanity.com/paper/2208.00647/) (2022)
- [Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data Acquisition](https://mlsanity.com/paper/2501.18268/) (2025)
- [Application of belief functions to medical image segmentation: A review](https://mlsanity.com/paper/2205.01733/) (2022)
- [Partial-Label Learning with a Reject Option](https://mlsanity.com/paper/2402.00592/) (2024)
- [Fusion of evidential CNN classifiers for image classification](https://mlsanity.com/paper/2108.10233/) (2021)
- [Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentation](https://mlsanity.com/paper/2208.00775/) (2022)
- [Deep evidential fusion with uncertainty quantification and contextual discounting for multimodal medical image segmentation](https://mlsanity.com/paper/2309.05919/) (2023)
- [ELC: Evidential Lifelong Classifier for Uncertainty Aware Radar Pulse Classification](https://mlsanity.com/paper/2604.06958/) (2026)
- [Feature Fusion for Improved Classification: Combining Dempster-Shafer Theory and Multiple CNN Architectures](https://mlsanity.com/paper/2405.20230/) (2024)
- [Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks](https://mlsanity.com/paper/2509.13338/) (2025)

## Abstract (arXiv)

We propose a new classifier based on Dempster-Shafer (DS) theory and a convolutional neural network (CNN) architecture for set-valued classification. In this classifier, called the evidential deep-learning classifier, convolutional and pooling layers first extract high-dimensional features from input data. The features are then converted into mass functions and aggregated by Dempster's rule in a DS layer. Finally, an expected utility layer performs set-valued classification based on mass functions. We propose an end-to-end learning strategy for jointly updating the network parameters. Additionally, an approach for selecting partial multi-class acts is proposed. Experiments on image recognition, signal processing, and semantic-relationship classification tasks demonstrate that the proposed combination of deep CNN, DS layer, and expected utility layer makes it possible to improve classification accuracy and to make cautious decisions by assigning confusing patterns to multi-class sets.