Hierarchical Graph Convolutional Networks for Image Classification.

Graph-based image representation is a promising research direction that can capture the structure and semantics of images. However, existing methods for converting images to graphs often fail to preserve the hierarchical information of the image elements and produce sub-optimal or poor regions. To address these limitations, we propose a novel approach that uses a hierarchical image segmentation technique to generate graphs at multiple segmentation scales, capturing the hierarchical relationships between image elements. We also propose and train a H ierarchical G raph C onvolutional Network for I mage C lassification (HGCIC) model that leverages the hierarchical information with three different adjacency setups on the CIFAR-10 database. Experimental results show that the proposed approach can achieve competitive or superior performance compared to other state-of-the-art methods while using smaller graphs.