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

TL;DR

This paper presents a novel ensemble method combining Dempster-Shafer Theory with multiple CNN architectures to improve classification accuracy and manage uncertainty in deep learning models, validated on CIFAR datasets.

Contribution

Introduces a DST-based ensemble algorithm that integrates multiple pre-trained CNNs for more reliable and accurate classification under uncertainty.

Findings

Achieved 5.4% and 8.4% accuracy improvements on CIFAR-10 and CIFAR-100.

Demonstrated DST's effectiveness in uncertainty management for deep learning.

Validated the approach with extensive experiments showing superior performance.

Abstract

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.