Knowledge Graph-Guided Deep Learning for Remote Sensing Image Understanding

Dear Colleagues,

As one of the most significant achievements in the artificial intelligence (AI) domain, deep learning has achieved tremendous success in remote sensing image understanding, including scene classification, semantic segmentation, and object detection. As is well known, deep learning is a classic data-driven technique and can often be trained in an end-to-end manner. As an inevitable disadvantage, it is incredibly difficult for deep learning to leverage the prior domain knowledge, which means common sense about remote sensing image interpretation and holds a natural generalization property. Despite deep learning’s aforementioned success in remote sensing image understanding, deep learning-based methods are susceptible to noise interference and lack the basic but vital cognition and inference ability. Consequently, deep learning still cannot fully meet the high-reliability demand of remote sensing image interpretation.

As another research hotspot in the field of AI, knowledge graphs work by explicitly representing the domain concepts and their relationships as a collection of triples and have strong knowledge representation capabilities and semantic reasoning capabilities. In order to fully reflect the domain characteristic of remote sensing, how to collaboratively construct a remote sensing knowledge graph with the aid of domain experts and data-driven methods deserves much more exploration. Based on remote sensing knowledge graphs, the semantic reasoning technique becomes very promising to fully leverage the rich semantic information in remote sensing images. Therefore, combining knowledge-driven knowledge graph reasoning and data-driven deep learning would be a promising research avenue to realize intelligent remote sensing image interpretation. The joint technique of knowledge graph reasoning and deep learning benefits assimilates the complementary advantages of these two techniques. It not only makes full use of the low-level and middle-level information mining ability of deep learning but also exerts the high-level semantic reasoning ability of knowledge graph reasoning.

This Special Issue calls for innovative remote sensing image understanding theory and methods by combining deep learning and knowledge graph reasoning. The topics include but are not limited to the following:

• Interpretive deep learning methods for remote sensing image understanding, including scene classification, semantic segmentation, and object detection;
• Domain knowledge modeling and reasoning for remote sensing image understanding;
• Data-driven remote sensing scene graph generation methods;
• Crowd-sourced remote sensing knowledge graph construction methods;
• High-reliability remote sensing image understanding methods by combining deep learning and knowledge reasoning;
• Representation learning of remote sensing knowledge graph for advanced remote sensing image understanding tasks: fine-grained image classification, few-shot image classification, zero-shot image classification, and so forth;
• Language-level remote sensing image understanding: image caption, visual question answering, cross-modal retrieval between text and images, and so forth;
• Large-scale and long-term remote sensing image understanding methods based on knowledge-guided deep learning.

Dr. Yansheng Li
Prof. Yongjun Zhang
Dr. Chen Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.