pisco_log
Training and Validation
Submission deadline: 2023-12-31
Section Collection Editors

Section Collection Information

Dear Colleagues,

With technical evolution in intelligent technology, remote sensing research has been advanced by recently appeared AI-based algorithms and frameworks, to achieve terrain mapping, meteorological monitoring, traffic management, human geography, etc. However, the rapid deveopment of these intelligent algorithms and machine learning frameworks requires increasing of training and validation data-set. Moreover, annotating and preparing data-set for experimental training and validation is laborious and tedious, and it is impractical when terabyte (TB) level data are acquired per day from a single remote sensing data center in the future. To tackle the current bottleneck in remote sensing, it is important and indispensable to improve training and validation procedures.

Therefore, we are interested in the collective novel self-supervised or unsupervised learning frameworks, self-annotation algorithms and data augment methods, few-shot training and validation strategies, machine learning in imbalanced or biased datasets, efficient methods to build new datasets, new open datasets, and datasets review for remote sensing.

For this, it is important to collect the method and strategies to solve the labor-intensive tasks in training and validation. Research articles and reviews in this area of study are welcome.

We look forward to receiving your contributions.


Dr. Mengyang Zhao

Section Editors


Keywords

Self-Supervised Learning; Unsupervised Learning; Few-Shot Learning; Self-Annotation; Data Augmentation; Imbalanced Dataset; Dataset Review

Published Paper