Abstract
Image classification is an important, real-world problem that arises in many contexts. To date, convolutional neural networks (CNNs) are the state-of-the-art deep learning method for image classification since these models are naturally suited to problems where the coordinates of the underlying data representation have a grid structure. On the other hand, in recent years, there is a growing interest in mapping data from different domains to graph structures. Such approaches proved to be quite successful in different domains including physics, chemoinformatics and natural language processing. In this paper, we propose to represent images as graphs and capitalize on well-established neural network architectures developed for graph-structured data to deal with image-related tasks. The proposed models are evaluated experimentally in image classification tasks, and are compared with standard CNN architectures. Results show that the proposed models are very competitive, and yield in most cases accuracies better or comparable to those of the CNNs.KeywordsGraph-based representationsGraph neural networksImage classification
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.