State-of-the-Art Remote Sensing Image Scene Classification

Dear Colleagues,

As a necessary precedent step, remote sensing scene classification assigns a specific semantic label to each image, which is very helpful for geological surveys, urban planning, and other fields. To identify remote sensing scenes, many machine learning techniques have been developed, such as logistic regression, neural networks, feature learning, and support vector machines. Although this research area has attracted much attention and achieved remarkable performance, most methods are based on an assumption: the training set and test set are drawn from the same distribution or data. In real-world applications, this assumption is frequently challenged, since the remote sensing scenes may be captured with different remote sensors and over diverse locations of the ground surface. Changes in sensor types, shooting angles and illumination condition can cause large distribution differences across remote sensing images. Therefore, the inclusion of a Special Issue in the journal Remote Sensing is right on time for promoting the innovation and improvement of remote sensing scene classification using cross-domain/multi-source data.

This Special Issue focuses on advances in remote sensing scene classification using cross-domain data, multi-source data, and multi-modal data. Topics of interest include, but are not limited to:

• Cross-domainremote sensing scene classification/cross-scene classification;
• Multi-source remote sensing data classification;
• Few-shot image classification;
• Multiple-scene or multi-task classification;
• Knowledge distillation and collaborative learning in remote sensing;
• A generalizable/domain-invariant/ transferable model for scene classification;
• Feature learning for cross-domain/multi-modal/multi-temporal image analysis;
• Applications/survey/benchmarkin remote sensing scene classification.

Dr. Xiangtao Zheng
Dr. Fulin Luo
Prof. Dr. Qi Wang
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.