# Fusion of evidential CNN classifiers for image classification

Source: [Fusion of evidential CNN classifiers for image classification](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294a7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:09:35.928Z

Authors: Zheng Tong, Philippe Xu, Thierry Denoeux

Published: 2021-08-23T15:12:26.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.10233>)

[PDF](<https://arxiv.org/pdf/2108.10233.pdf>)