About Abdullah Hamdi Abdullah Hamdi Ph.D., Electrical and Computer Engineering Deep learning machine learning Computer Vision Abdullah Hamdi was a Ph.D. student in the Image and Video Understanding Lab (IVUL) Group at King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Bernard Ghanem. Education and Early Career In 2016, Abdullah Hamdi obtained his bachelor's degree in Electrical Engineering from King Fahd University of Petroleum and Minerals (KFUPM) in Dhahran, Saudi Arabia. After that, he joined KAUST to pursue the same field of study and received his master's degree in 2017 in the Computer Vision track. Research Interest Machine Learning Robustness of Deep Learning Computer Events Presented Events Apr 9 - Apr 15, 2023 Towards Designing Robust Deep Learning Models for 3D Understanding Abdullah Hamdi, Ph.D., Electrical and Computer Engineering Apr 10, 17:00 - 19:00 B3 L5 R5220 deep neural networks Deep Neural Networks (DNNs) have shown huge success over the years to solve many 2D computer vision tasks driven by massive labeled 2D datasets and advancements in 2D vision models, but less success is witnessed on 3D vision tasks. This dissertation proposes innovative approaches to enhance the robustness of DNNs for 3D understanding and in 3D settings. The research focuses on two main areas: adversarial robustness on 3D data and setups, and the robustness of DNNs to realistic 3D scenarios. Two paradigms for 3D understanding are discussed: representing 3D as a set of 3D points and performing 2D processing of multiple images of the 3D data.
Towards Designing Robust Deep Learning Models for 3D Understanding Abdullah Hamdi, Ph.D., Electrical and Computer Engineering Apr 10, 17:00 - 19:00 B3 L5 R5220 deep neural networks Deep Neural Networks (DNNs) have shown huge success over the years to solve many 2D computer vision tasks driven by massive labeled 2D datasets and advancements in 2D vision models, but less success is witnessed on 3D vision tasks. This dissertation proposes innovative approaches to enhance the robustness of DNNs for 3D understanding and in 3D settings. The research focuses on two main areas: adversarial robustness on 3D data and setups, and the robustness of DNNs to realistic 3D scenarios. Two paradigms for 3D understanding are discussed: representing 3D as a set of 3D points and performing 2D processing of multiple images of the 3D data.
Related Sites Center of Excellence for Generative AI (GenAI) Electrical and Computer Engineering (ECE) Image and Video Understanding Lab (IVUL) Related Content Articles 6 Events 1 Related Links Also view list of Publications on KAUST Repository Visual Computing Center (VCC) Fihm.ai (Arabic AI Blog) Personal Website
