Avatar

Abdullah Hamdi

PhD Student; Electrical Engineering (Computer Vision)

King Abdullah University of Science and Technology

Biography

I’m a PhD student at King Abdullah University of Science and Technology (KAUST), pursuing to advance artificial intelligence via understanding deep neural networks. I am part of the Image and Video Understanding Laboratory (IVUL) in the Visual Computing Center (VCC), advised by Bernard Ghanem. I received my MSc degree in Electrical Engineering (Computer Vision) from KAUST, and my undergraduate degree form King Fahd University of Petroleum and Minerals (KFUPM) in Electrical Engineering. I want to develop innovative solutions to human difficult problems based on AI tools. Specifically, I want to utilize less explored adversarial capabilities of deep learning. Here is a video and an article about me explaining my future vision and my current work.

Interests

  • Machine Learning
  • Robustness of Deep Learning
  • Computer Vision
  • GANs
  • Simulation for Vision

Education

  • MSc in Electrical Engineering (GPA 4/4), 2018

    King Abdullah University of Science and Technology

  • BSc in Electrical Engineering (GPA 3.97/4), 2016

    King Fahd University of Petroleum and Minerals

Videos

Featured Publications

SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications

One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for …

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds

Deep neural networks are vulnerable to adversarial attacks, in which imperceptible perturbations to their input lead to erroneous …

Towards Analyzing Semantic Robustness of Deep Neural Networks

Despite the impressive performance of Deep Neural Networks (DNNs) on various vision tasks, they still exhibit erroneous high …

IAN: Combining Generative Adversarial Networks for Imaginative Face Generation

Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the …

Cascading Generative Adversarial Networks for Targeted Imagination

Abundance of labelled data played a crucial role in the recent developments in computer vision, but that faces problems like …

Smart dust-cleaner and cooler for solar PV panels

The smart dust-cleaner and cooler for solar photo-voltaic (PV) panels is a smooth transparent shield with low absorption coefficient …

Learning Rotation for Kernel Correlation Filter

Kernel Correlation Filters have shown a very promising scheme for visual tracking in terms of speed and accuracy on several benchmarks. …

Skills

Python

Pytorch/TensorFlow

Game Engines

Blender, UE4 , Unity

Contact