论文标题
PK-GCN：使用图形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
论文作者
论文摘要
深度学习在各种分类任务中取得了巨大的成功。通常，深度学习模型直接从数据中学习潜在的功能，并且不包括类之间的潜在关系。班级之间的相似性会影响分类的性能。在本文中，我们提出了一种使用图卷积层将类相似性知识纳入卷积神经网络模型中的方法。我们在两个基准图像数据集上评估我们的方法：MNIST和CIFAR10，并分析不同数据和模型大小的结果。实验结果表明，我们的模型可以提高分类准确性，尤其是当可用数据量较小时。
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.
