PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks

by   Xueli Xiao, et al.

Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes can influence the performance of classification. In this article, we propose a method that incorporates class similarity knowledge into convolutional neural networks models using a graph convolution layer. We evaluate our method on two benchmark image datasets: MNIST and CIFAR10, and analyze the results on different data and model sizes. Experimental results show that our model can improve classification accuracy, especially when the amount of available data is small.


page 1

page 2

page 3

page 4


Medical Knowledge-Guided Deep Learning for Imbalanced Medical Image Classification

Deep learning models have gained remarkable performance on a variety of ...

A Quantum Spatial Graph Convolutional Neural Network using Quantum Passing Information

In this paper, we develop a new Quantum Spatial Graph Convolutional Neur...

Semi-supervised Hyperspectral Image Classification with Graph Clustering Convolutional Networks

Hyperspectral image classification (HIC) is an important but challenging...

On Graph Classification Networks, Datasets and Baselines

Graph classification receives a great deal of attention from the non-Euc...

Unsupervised Feature Learning for Writer Identification and Writer Retrieval

Deep Convolutional Neural Networks (CNN) have shown great success in sup...

Simultaneous Classification and Novelty Detection Using Deep Neural Networks

Deep neural networks have achieved great success in classification tasks...

Please sign up or login with your details

Forgot password? Click here to reset