Islam I. Osman

According to our database, Islam I. Osman authored at least 9 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2024

Fully Self-Supervised Out-of-Domain Few-Shot Learning with Masked Autoencoders.

Reece Walsh, Islam I. Osman, Omar Abdelaziz, Mohamed S. Shehata

J. Imaging, January, 2024

2023

Few-Shot Learning Network for Out-of-Distribution Image Classification.

Islam I. Osman, Mohamed S. Shehata

IEEE Trans. Artif. Intell., December, 2023

Masked Embedding Modeling With Rapid Domain Adjustment for Few-Shot Image Classification.

Reece Walsh, Islam I. Osman, Mohamed S. Shehata

IEEE Trans. Image Process., 2023

Domain Generalization for Foreground Segmentation Using Federated Learning.

Islam I. Osman, Islam Abdelfattah, Mohamed S. Shehata

Proceedings of the Advances in Visual Computing - 18th International Symposium, 2023

2022

Few-Shot Learning Network for Moving Object Detection Using Exemplar-Based Attention Map.

Islam I. Osman, Mohamed S. Shehata

Proceedings of the 2022 IEEE International Conference on Image Processing, 2022

Self-supervised Learning for Foreground Segmentation with a Few Amount of Labeled Images Using Transformers.

Islam I. Osman, Mohamed S. Shehata

Proceedings of the 8th International Conference on Advanced Intelligent Systems and Informatics, 2022

2021

Task-based parameter isolation for foreground segmentation without catastrophic forgetting using multi-scale region and edges fusion network.

Islam I. Osman, Agwad ElTantawy, Mohamed S. Shehata

Image Vis. Comput., 2021

TransBlast: Self-Supervised Learning Using Augmented Subspace with Transformer for Background/Foreground Separation.

Islam I. Osman, Mohamed H. Abdelpakey, Mohamed S. Shehata

Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2021

2020

MODSiam: Moving Object Detection using Siamese Networks.

Islam I. Osman, Mohamed S. Shehata

Proceedings of the IEEE Canadian Conference on Electrical and Computer Engineering, 2020