Fusion of evidential CNN classifiers for image classification

TL;DR

This paper introduces an innovative method that combines multiple CNN classifiers using belief functions and Dempster's rule, enhancing image classification accuracy through end-to-end learning on benchmark datasets.

Contribution

It presents a novel information-fusion framework that integrates pre-trained CNNs with belief functions and Dempster's rule, optimized via end-to-end training.

Findings

Improved classification accuracy on benchmark datasets

Effective fusion of multiple CNN features using belief functions

End-to-end training enhances overall performance

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.