Skip to main content
User Image

Dr. Belgacem Ben Youssef

Associate Professor

Associate Professor

علوم الحاسب والمعلومات
bbenyoussef@KSU.EDU.SA
publication
Journal Article
2024

Federated Learning Approach for Remote Sensing Scene Classification

In classical machine learning algorithms, used in many analysis tasks, the data are cen-
tralized for training. That is, both the model and the data are housed within one device. Federated
learning (FL), on the other hand, is a machine learning technique that breaks away from this tradi-
tional paradigm by allowing multiple devices to collaboratively train a model without each sharing
their own data. In a typical FL setting, each device has a local dataset and trains a local model on
that dataset. The local models are next aggregated at a central server to produce a global model. The global model is then distributed back to the devices, which update their local models accordingly.
This process is repeated until the global model converges. In this article, a FL approach is applied for
remote sensing scene classification for the first time. The adopted approach uses three different RS
datasets while employing two types of CNN models and two types of Vision Transformer models,
namely: EfficientNet-B1, EfficientNet-B3, ViT-Tiny, and ViT-Base. We compare the performance of
FL in each model in terms of overall accuracy and undertake additional experiments to assess their
robustness when faced with scenarios of dropped clients. Our classification results on test data
show that the two considered Transformer models outperform the two models from the CNN family.
Furthermore, employing FL with ViT-Base yields the highest accuracy levels even when the number
of dropped clients is significant, indicating its high robustness. These promising results point to the
notion that FL can be successfully used with ViT models in the classification of RS scenes, whereas
CNN models may suffer from overfitting problems.

Publisher Name
MDPI
Volume Number
16
Issue Number
12
Magazine \ Newspaper
Remote Sensing
more of publication
publications

In classical machine learning algorithms, used in many analysis tasks, the data are cen-
tralized for training. That is, both the model and the data are housed within one device. Federated…

by B. Ben Youssef, L. Alhmidi, Y. Bazi, and M. Zuair
2024
Published in:
MDPI
publications

In the field of satellite imaging, effectively managing the enormous volumes of data from remotely sensed hyperspectral images presents significant challenges due to the limited bandwidth and…

by A. Altamimi and B. Ben Youssef
2024
Published in:
MDPI
publications

The square root operation is indispensable in a myriad of computational science and engineering applications. Various computational techniques have been devised to approximate its value. In…

by A. Altamimi and B. Ben Youssef
2022
Published in:
Springer Nature