About this Research Topic
Modern machine learning and deep learning approaches have shown great potential in addressing the limitations of supervised learning when working with limited data. These approaches are highly effective in general-purpose machine learning and computer vision tasks, enabling the learning process from limited data, transferring knowledge across domains, and adaptation to new tasks with minimal labelled examples. Despite their success in various domains, these methods have limited applicability in complex remote sensing data due to their unique characteristics such as physical meaning, multi-modality, and noise, coupled with the limited availability of data. Therefore, research on modern advances in remote sensing under limited data has become critical to explore new techniques that can overcome these limitations and harness the full potential of remote sensing data.
The goal of this Research Topic is to explore and present recent advances in machine learning and deep learning techniques for remote sensing under limited data. It aims to showcase significant, innovative, and effective approaches that address the challenges associated with limited data availability, such as self-supervised, few-shot, and meta-learning techniques. We are particularly interested in contributions that demonstrate the practical applicability of these methods to real-world remote sensing problems. Through this themed article collection, we aim to inspire and inform researchers working in the field, providing them with insights into state-of-the-art techniques and identifying promising directions for future research. Ultimately, the goal is to advance the state-of-the-art in remote sensing applications, improving their accuracy and reliability for a wide range of real-world problems.
We invite original research articles, surveys, and other papers that explore the intersection of artificial intelligence and remote sensing under limited data. We welcome submissions that apply novel machine learning and deep learning approaches as well as state-of-the-art techniques to address the unique challenges posed by remote sensing data, particularly in the context of limited data availability. Specific themes of interest include but are not limited to:
- Few-shot learning
- Meta-learning
- Transfer learning
- Self-supervised learning
- Informed machine learning
- Novel feature learning strategies
We are particularly interested in contributions that demonstrate the practical applicability of these techniques to real-world remote sensing problems. Manuscripts that describe innovative approaches and present new insights into the application of artificial intelligence to remote sensing tasks are particularly welcome.
The goal of this Research Topic is to explore and present recent advances in machine learning and deep learning techniques for remote sensing under limited data. It aims to showcase significant, innovative, and effective approaches that address the challenges associated with limited data availability, such as self-supervised, few-shot, and meta-learning techniques. We are particularly interested in contributions that demonstrate the practical applicability of these methods to real-world remote sensing problems. Through this themed article collection, we aim to inspire and inform researchers working in the field, providing them with insights into state-of-the-art techniques and identifying promising directions for future research. Ultimately, the goal is to advance the state-of-the-art in remote sensing applications, improving their accuracy and reliability for a wide range of real-world problems.
We invite original research articles, surveys, and other papers that explore the intersection of artificial intelligence and remote sensing under limited data. We welcome submissions that apply novel machine learning and deep learning approaches as well as state-of-the-art techniques to address the unique challenges posed by remote sensing data, particularly in the context of limited data availability. Specific themes of interest include but are not limited to:
- Few-shot learning
- Meta-learning
- Transfer learning
- Self-supervised learning
- Informed machine learning
- Novel feature learning strategies
We are particularly interested in contributions that demonstrate the practical applicability of these techniques to real-world remote sensing problems. Manuscripts that describe innovative approaches and present new insights into the application of artificial intelligence to remote sensing tasks are particularly welcome.
Keywords: Remote Sensing, Limited Data, Pattern Recognition, Machine learning, Few-shot learning, Self-supervised learning, Meta-learning, Transfer learning, Earth observation
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
