Deep Learning for Remote Sensing Image Segmentation

Dear Colleagues,

Image segmentation is one of the most fundamental tasks in remote sensing, supporting applications such as land-cover and land-use mapping, urban planning, precision agriculture, forest and wetland monitoring, disaster assessment, and change detection. Over the past decade, deep learning has transformed this field. Convolutional neural networks, encoder–decoder architectures, and more recently Vision Transformers and foundation models have dramatically improved the accuracy and scalability of semantic, instance, and panoptic segmentation across optical, multispectral, hyperspectral, SAR, and LiDAR-derived data. At the same time, the rapidly growing volume and diversity of Earth observation data, together with the unique characteristics of remote sensing imagery, including large scene sizes, multi-scale objects, spectral richness, class imbalance, and scarce annotations, continue to pose significant challenges that motivate dedicated methodological research.

This Special Issue aims to bring together recent advances in deep learning methods for remote sensing image segmentation and to support the development of accurate, efficient, robust, and generalizable models for real-world Earth observation. Aligned with the scope of Remote Sensing, we welcome contributions that advance the state of the art in segmentation algorithms and demonstrate their value across diverse sensors, platforms, and application domains. We invite submissions of original research articles, review papers, and benchmark and dataset papers.

Topics of interest include, but are not limited to:

• Semantic, instance, and panoptic segmentation of remote sensing imagery;
• Transformer-based architectures, promptable segmentation models, vision language models, and foundation models for remote sensing image segmentation;
• Weakly supervised, semi-supervised, self-supervised, few-shot, zero-shot, and open-vocabulary segmentation;
• Domain adaptation and transfer learning for cross-sensor or cross-region segmentation;
• Multi-modal and multi-temporal segmentation fusing optical, SAR, hyperspectral, and LiDAR-derived data;
• Efficient, lightweight, and real-time segmentation for onboard and edge processing;
• Uncertainty estimation, explainability, and trustworthy segmentation models;
• New benchmark datasets and applications in land cover, agriculture, forestry, water, urban mapping, and disaster monitoring.

Dr. Zhenghang Yuan
Dr. Lanlan Rao
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-anonymized 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.