# Feature Fusion for Improved Classification: Combining Dempster-Shafer Theory and Multiple CNN Architectures

arXiv: https://arxiv.org/abs/2405.20230 · HTML: https://mlsanity.com/paper/2405.20230/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 23 May 2024.

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

- [Bayes in the age of intelligent machines](https://mlsanity.com/paper/2311.10206/) (2023)
- [An evidential classifier based on Dempster-Shafer theory and deep learning](https://mlsanity.com/paper/2103.13549/) (2021)
- [Logistic Regression, Neural Networks and Dempster-Shafer Theory: a New Perspective](https://mlsanity.com/paper/1807.01846/) (2018)
- [A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation](https://mlsanity.com/paper/2204.02779/) (2022)
- [Gaussian Process Surrogate Models for Neural Networks](https://mlsanity.com/paper/2208.06028/) (2022)
- [CNN-DST: ensemble deep learning based on Dempster-Shafer theory for vibration-based fault recognition](https://mlsanity.com/paper/2110.07191/) (2021)

## Abstract (arXiv)

Addressing uncertainty in Deep Learning (DL) is essential, as it enables the development of models that can make reliable predictions and informed decisions in complex, real-world environments where data may be incomplete or ambiguous. This paper introduces a novel algorithm leveraging Dempster-Shafer Theory (DST) to integrate multiple pre-trained models to form an ensemble capable of providing more reliable and enhanced classifications. The main steps of the proposed method include feature extraction, mass function calculation, fusion, and expected utility calculation. Several experiments have been conducted on CIFAR-10 and CIFAR-100 datasets, demonstrating superior classification accuracy of the proposed DST-based method, achieving improvements of 5.4% and 8.4%, respectively, compared to the best individual pre-trained models. Results highlight the potential of DST as a robust framework for managing uncertainties related to data when applying DL in real-world scenarios.