Few-Sample Intelligence for Hyperspectral Remote Sensing Image Classification
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: 15 August 2026 | Viewed by 29
Special Issue Editors
Interests: machine/deep learning foundations for remote sensing; remote sensing image classification; object detection; semantic segmentation; change detection; anomaly detection
Special Issues, Collections and Topics in MDPI journals
Interests: machine learning; remote sensing image processing; spectral imaging non-destructive detection
Special Issues, Collections and Topics in MDPI journals
Interests: remote sensing big data processing; machine learning; data mining; artificial intelligence
Special Issue Information
Dear Colleagues,
Hyperspectral remote sensing imagery, characterized by its contiguous and narrow spectral bands, provides an unparalleled data source for the precise identification and classification of ground targets. However, its high dimensionality and the fundamental scarcity of labeled training samples severely limit its practical application. While artificial intelligence techniques with deep learning, as a typical example, have revolutionized hyperspectral image analysis, their success often depends on large annotated datasets that are costly and time-consuming to acquire in hyperspectral remote sensing. This challenge has catalyzed the emergence of few-sample intelligence—a dedicated research frontier focused on developing AI models that learn effectively from minimal labeled data. Techniques such as meta-learning, generative data augmentation, and self-supervised pre-training are pushing the boundaries of what is achievable with limited supervision. Advancing few-sample intelligence is critical for unlocking the operational potential of hyperspectral technology across scientific and commercial applications where annotation resources are constrained.
This Special Issue aims to compile cutting-edge research on AI methods specifically designed for few-sample intelligence for hyperspectral image classification. Topics of interest span all aspects of this domain, from novel algorithms that improve labeled sample efficiency and generalization, to innovative strategies for leveraging unlabeled or auxiliary data, and rigorous evaluations in real-world scenarios. This issue particularly encourages submissions addressing challenges such as cross-domain few-shot adaptation, uncertainty-aware learning with small data, and the integration of physical models or knowledge to guide few-sample learning. Its focus directly is directly aligned with the journal’s aim of publishing significant research on the science and application of remote sensing technology.
Articles may address, but are not limited to, the following topics:
- Few-shot and zero-shot learning;
- Meta-learning and active learning;
- Semi-supervised and weakly supervised learning;
- Transfer learning and domain adaptation;
- Self-supervised and unsupervised pre-training;
- Lightweight and efficient networks for small data;
- Generative models for spectral–spatial data augmentation;
- Multi-modal fusion with limited samples;
- Sample uncertainty quantification in classification;
- Few-sample classification for fine-grained agriculture, geology, and urban monitoring.
Research articles and 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.
Prof. Dr. Fulin Luo
Prof. Dr. Yule Duan
Prof. Dr. Xiaohui He
Dr. Guangyao Shi
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.
Keywords
- hyperspectral image classification
- few-sample classification
- semi-supervised classification
- few-shot learning
- self-supervised training
- cross-scene transfer learning
- multi-modal fusion classification
- fine-grained land cover mapping
- lightweight models
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
