arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.11892cs.CVcs.LGeess.IV
收藏

PK-GCN:基于图卷积网络的先验知识辅助图像分类

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

Georgia State University(佐治亚州立大学);Computer Science Department(计算机科学系)

Xueli Xiao, Chunyan Ji, Thosini Bamunu Mudiyanselage, Yi Pan

摘要:

深度学习在各种分类任务中取得了巨大成功。通常,深度学习模型直接从数据中学习底层特征,并且不包括类之间的底层关系。类之间的相似性会影响分类的性能。在这篇文章中,我们提出了一种使用图卷积层将类相似性知识并入卷积神经网络模型的方法。我们在两个基准图像数据集:MNIST和CIFAR10上评估了我们的方法,并分析了不同数据和模型大小的结果。实验结果表明,该模型可以提高分类精度,特别是当可用数据量很小时。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑