About Me

Hi, this is Kaleab (ቃለአብ). I am a PhD student at Johns Hopkins University, where I am affiliated with the Mathematical Institute for Data Science and have been extremely fortunate to be advised by Prof. René Vidal and Prof. Joshua Vogelstein. I am also an alumni of Erasmus Mundus Master's Joint Program in Image Processing and Computer Vision, where I was very grateful to work as a Research Assistant at VPU Lab of the Autonomous University of Madrid and as a Scientific Employee at TU Graz Institute of Computer Graphics and Vision to do my Master’s thesis on ‘Lifelong learning on Autonomous Vehicles’ under the supervision of Prof. Horst Bischof.

My research interests are in Image Processing, Computer Vision, and Machine Learning.

I'm extremely enthusiastic about AI and its power to make our world a better place to live; and I want to contribute my part on this captivating and wonderful scientific field working to solve the open problems in Computer Vision and Machine Learning so as to build autonomous systems that can "see" and reason.


Experience and Education

  Download Résume

  Social Media

  Programming Languages









  IPCV Coursework

Computer Vision
Machine Learning

Augmented Reality
Deep Learning

Prob/Stat Inference
IT Management


  Studied in



  • X (formerly Google X)

    PhD Resident

    Mountain View, CA

  • Microsoft Research

    Research Intern

    Redmond, WA

    • Team: Special Projects.
  • Mathematic Institute for Data Science, JHU

    Research Assistant

    Baltimore, MD

    • Working under the supervision of Prof. René Vidal on numerous computer vision and machine learning tasks including adversarial defense for action recognition networks, 2D and 3D human pose estimation, and video understanding.
  • NeuroData, JHU

    Research Assistant

    Baltimore, MD

    • Working under the supervision of Prof. Joshua T. Vogelstein on a state-of-the-art framework called progressive learning that realizes backward and forward knowledge transfer
  • TU Graz Institute of Computer Graphics and Vision

    Research Associate

    Graz, Austria

    • We investigated CNN based methods for the task of continual lifelong learning for autonomous vehicles learning problems.
  • The Cornell, Maryland, Max Planck Pre-doctoral Research School

    Emerging Research Trends in Computer Science

    Saarbrücken, Germany

    • Learnt about cutting-edge research in CS and exposed to state-of-the-art research in computer science, had the opportunity to interact one-on-one with internationally leading scientists from three of the foremost academic institutions in research and higher learning.
  • VPU Lab, Autonomous University of Madrid

    Research Intern

    Madrid, Spain

    • Worked on a tool for the automatic generation of ground-truth data for object detection of Google Street View images.
    • A multi-projection variant of YOLO detector for Equirectangular Panorama, specifically Google Street View images.
  • Pázmány Péter Catholic University, Hungary

    MSc in Computer Science Engineering, Honours

  • Autonomous University of Madrid, Spain

    MSc in Image Processing and Computer Vision, Honours

  • University of Bordeaux, France

    MSc in Computer Science, mention très bien

  • Addis Ababa University, Ethiopia

    Assistant Lecturer

    Addis Ababa, Ethiopia

    • Develop own teaching materials, methods and approaches taking into account established or agreed practices where necessary.
  • Addis Ababa University, Ethiopia

    BSc in Computer Science, Very Great Distinction

    Bachelor's Thesis Title: 'An Autonomous Traffic Management System'



Extensions of Adversarial Training for Video Classification

Lifelong Learning for Autonomous Vehicles

Multi-task learning of Monocular Depth Estimation and Segmentation from Video

3D Shape Prediction from Single RGB Image using Deep Learning

Ground-truth generation for Google Street View images

Ethiopian Sign Language to Amharic Text Translator

Automated Optical Mark Reader

Intelligent Traffic Management System

Multiple Object Recognition using Deep Learning

Abugida: Educational App for Preschoolers

Face Recognition | Body Tracking


Currently studying CS/BME Data Science @ Johns Hopkins University!

Addis Ababa University Pázmány Péter Catholic University Autonomous University of Madrid The Cornell, Maryland, Max Planck Pre-doctoral Research School The Cornell, Maryland, Max Planck Pre-doctoral Research School The Cornell, Maryland, Max Planck Pre-doctoral Research School University of Bordeaux Graz University of Technology Johns Hopkins University
The Vision Lab Family attending CVPR at New Orleans, LA, 2022!
The NeuroData Lab Family at Johns Hopkins University, 2022!
@The Cornell, Maryland, Max Planck Pre-doctoral Research School, 2019!
The IPCV Family at UAM, Spain, 2019!