PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks
Computer Vision and Pattern Recognition
2020-09-28 v1 Machine Learning
Image and Video Processing
Abstract
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.
Keywords
Cite
@article{arxiv.2009.11892,
title = {PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks},
author = {Xueli Xiao and Chunyan Ji and Thosini Bamunu Mudiyanselage and Yi Pan},
journal= {arXiv preprint arXiv:2009.11892},
year = {2020}
}