# Fusion of evidential CNN classifiers for image classification

arXiv: https://arxiv.org/abs/2108.10233 · HTML: https://mlsanity.com/paper/2108.10233/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 23 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [An evidential classifier based on Dempster-Shafer theory and deep learning](https://mlsanity.com/paper/2103.13549/) (2021)
- [Bayesian Fusion of Multi-Band Images](https://mlsanity.com/paper/1307.5996/) (2013)
- [Decision-Making with Belief Functions: a Review](https://mlsanity.com/paper/1808.05322/) (2018)
- [Decision under Uncertainty](https://mlsanity.com/paper/1304.1527/) (2013)
- [Evidential fully convolutional network for semantic segmentation](https://mlsanity.com/paper/2103.13544/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation](https://mlsanity.com/paper/2410.18461/) (2024)

## Abstract (arXiv)

We propose an information-fusion approach based on belief functions to combine convolutional neural networks. In this approach, several pre-trained DS-based CNN architectures extract features from input images and convert them into mass functions on different frames of discernment. A fusion module then aggregates these mass functions using Dempster's rule. An end-to-end learning procedure allows us to fine-tune the overall architecture using a learning set with soft labels, which further improves the classification performance. The effectiveness of this approach is demonstrated experimentally using three benchmark databases.