Graph-based deep learning techniques for remote sensing applications: Techniques, taxonomy, and applications - A comprehensive review

In the last decade, there has been a significant surge of interest in machine learning, primarily driven by advancements in deep learning (DL). DL has emerged as a powerful solution to address various challenges in numerous fields, including remote sensing (RS). Graph Deep Learning (GDL), a sub-field of DL, has recently gained increasing attention in the RS community. Tasks in RS requiring detailed information about the relationships between image/scene features are particularly well-suited for GDL. This study examines the notion of GDL and its recent developments in RS-related fields. An extensive survey of the current state-of-the-art in GDL is presented in this paper, with a specific emphasis on five established graph learning techniques: Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), Graph Recurrent Neural Networks (GRNNs), Graph Auto-encoders (GAEs), and Graph Generative Adversarial Networks (GGANs). A taxonomy is proposed based on the input data type (dynamic or static) or task being considered. Several promising research directions for GDL in RS are suggested in this paper to foster productive collaborations between the two domains. To the best of our knowledge, this study is the first to provide a comprehensive review that focuses on graph deep learning in remote sensing.

Automated summary

This study investigates the recent developments of graph deep learning (GDL) in the field of remote sensing. It presents an extensive survey of the current state-of-the-art in GDL, with a specific focus on five established graph learning techniques. A taxonomy is proposed based on the input data type or task being considered, and several promising research directions are suggested to promote collaborations between the domains. This study is the first comprehensive review of graph deep learning in remote sensing.