Improving correlation method with convolutional neural networks

04/20/2020

∙

We present a convolutional neural network for the classification of correlation responses obtained by correlation filters. The proposed approach can improve the accuracy of classification, as well as achieve invariance to the image classes and parameters.

READ FULL TEXT

Improving correlation method with convolutional neural networks

Equivariant neural networks and equivarification

State Classification of Cooking Objects Using a VGG CNN

Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation

Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks

Neuronal Correlation: a Central Concept in Neural Network

Using Convolutional Neural Networks for the Helicity Classification of Magnetic Fields

On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks

Improving correlation method with convolutional neural networks

Related Research

Equivariant neural networks and equivarification

State Classification of Cooking Objects Using a VGG CNN

Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation

Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks

Neuronal Correlation: a Central Concept in Neural Network

Using Convolutional Neural Networks for the Helicity Classification of Magnetic Fields

On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks