GRSS Special Stream on Restricted Label Learning for Remote Sensing Image Interpretation
Remote sensing images generally contain rich spatial-spectral-temporal information to monitor and model natural as well as man-made processes. The increasing number of air- and spaceborne sensors collects a large amount of data on a daily basis. While there are many advanced intelligent algorithms designed for remote sensing image interpretation, their robustness and accuracy depends on large training datasets. In practice, remote sensing image labeling requires extensive professional knowledge and sometimes even in-situ measurements. Thus, large-scale training datasets are hard or even impossible to obtain in many applications, hindering the construction of accurate and robust models through fully-supervised learning. To conquer the label reliance of machine learning models and being able to achieve an accurate and robust interpretation of remote sensing images, solutions are required that enable the training of models with datasets with limited labeled samples only.
This IEEE GRSL Special Stream calls for restricted label related contributions to the remote sensing domain. Possible topics include (but are not limited to):
- Semi-supervised learning
- Weakly-supervised learning
- Self-supervised learning
- Cross domain learning
- Few-shot learning
- Meta-learning
- Contrastive learning
- Large model fine-tuning
- Foundation models
- New restricted datasets
Guest Editors:
- Fulin Luo, Chongqing University, Chongqing, China (Lead Guest Editor)
- Yanni Dong, Wuhan University, Wuhan, China (Guest Editor)
- Mohammad Awrangjeb, Griffith University, Australia (Guest Editor)
- Jinchang Ren, Robert Gordon University, United Kingdom (Guest Editor)
- Jocelyn Chanussot, Grenoble Institute of Technology, France (Guest Editor)
Schedule:
Submission open: October 1, 2024
Submission close: December 31, 2024
All submissions must be formatted using the IEEE standard format (double-column, single-spaced) typically 4-5 pages. Please use the following link to download the article template. All submissions will be peer-reviewed according to the GRSS guidelines. Submitted articles should not have been published or be under review elsewhere. Submit your manuscript to mc.manuscriptcentral.com/grsl, using the Manuscript Central interface, and select our specific stream. Accepted papers are subject to GRSL’s usual publication charges.
