Radial Basis Function Networks for Convolutional Neural Networks to Learn Similarity Distance Metric and Improve Interpretability

08/24/2022
by   Mohammadreza Amirian, et al.
9

Radial basis function neural networks (RBFs) are prime candidates for pattern classification and regression and have been used extensively in classical machine learning applications. However, RBFs have not been integrated into contemporary deep learning research and computer vision using conventional convolutional neural networks (CNNs) due to their lack of adaptability with modern architectures. In this paper, we adapt RBF networks as a classifier on top of CNNs by modifying the training process and introducing a new activation function to train modern vision architectures end-to-end for image classification. The specific architecture of RBFs enables the learning of a similarity distance metric to compare and find similar and dissimilar images. Furthermore, we demonstrate that using an RBF classifier on top of any CNN architecture provides new human-interpretable insights about the decision-making process of the models. Finally, we successfully apply RBFs to a range of CNN architectures and evaluate the results on benchmark computer vision datasets.

READ FULL TEXT

page 1

page 2

page 4

page 6

page 7

page 9

page 10

page 12

research
05/27/2017

Nearest Neighbour Radial Basis Function Solvers for Deep Neural Networks

We present a radial basis function solver for convolutional neural netwo...
research
07/28/2018

PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks

Recently, Convolutional Neural Networks (CNNs) have dominated the field ...
research
01/07/2020

Inferring Convolutional Neural Networks' accuracies from their architectural characterizations

Convolutional Neural Networks (CNNs) have shown strong promise for analy...
research
11/03/2020

Similarity-Based Clustering for Enhancing Image Classification Architectures

Convolutional networks are at the center of best in class computer visio...
research
12/21/2019

Convolutional Neural Networks: A Binocular Vision Perspective

It is arguable that whether the single camera captured (monocular) image...
research
10/16/2021

An Acceleration Method Based on Deep Learning and Multilinear Feature Space

Computer vision plays a crucial role in Advanced Assistance Systems. Mos...

Please sign up or login with your details

Forgot password? Click here to reset