{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/superpixel-image-classification-with-graph","title":"Superpixel Image Classification with Graph Attention Networks","arxiv_id":"2002.05544","date":"2020-02-13","proceeding":null,"authors":["Pedro H. C. Avelar","Anderson R. Tavares","Thiago L. T. da Silveira","Cláudio R. Jung","Luís C. Lamb"],"abstract":"This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-attention mechanisms, outperforms other GNN models. Although raw image classifiers perform better than GATs due to information loss during the RAG generation, our methodology opens an interesting avenue of research on deep learning beyond rectangular-gridded images, such as 360-degree field of view panoramas. Traditional convolutional kernels of current state-of-the-art methods cannot handle panoramas, whereas the adapted superpixel algorithms and the resulting region adjacency graphs can naturally feed a GNN, without topology issues.","url_abs":"https://arxiv.org/abs/2002.05544v2","url_pdf":"https://arxiv.org/pdf/2002.05544v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"superpixel-image-classification-with-graph","repo_url":"https://github.com/machine-reasoning-ufrgs/spixel-gat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"superpixel-image-classification","task_name":"Superpixel Image Classification"},{"task_slug":"superpixels","task_name":"Superpixels"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/superpixel-image-classification-on-75","task":"Superpixel Image Classification","dataset":"75 Superpixel MNIST","model":"GAT","rank_in_archive_order":3,"of":6,"metrics":{"Classification Error":"3.81"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}