PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks
arXiv:2009.11892
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.
References in corpus (11)
- Semi-Supervised Classification with Graph Convolutional Networks
- Large-Scale Evolution of Image Classifiers
- Data Augmentation using Random Image Cropping and Patching for Deep CNNs
- Data Augmentation by Pairing Samples for Images Classification
- Harnessing Deep Neural Networks with Logic Rules
- Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
- Hybrid Knowledge Routed Modules for Large-scale Object Detection
- A Semantic Loss Function for Deep Learning with Symbolic Knowledge
- Graph Convolutional Networks for Classification with a Structured Label Space
- Gradient Amplification: An efficient way to train deep neural networks
- ClassSim: Similarity between Classes Defined by Misclassification Ratios of Trained Classifiers