Back to Search
Start Over
Fusion of evidential CNN classifiers for image classification
- Publication Year :
- 2021
-
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.
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2108.10233
- Document Type :
- Working Paper