Fusion of evidential CNN classifiers for image classification

08/23/2021
by   Zheng Tong, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset