Özgür Kara

prof_pic.jpg

CODA, 15th Floor

756 West Peachtree Street

Atlanta, GA, USA, 30332

Currently, I am a 1st year PhD student at Georgia Institute of Technology, Machine Learning PhD program under the supervision of Professor James Rehg.

From a high-level perspective, my research focuses on various downstream problems in 3D and 2D computer vision. My long-term research goal seeks to develop generalizable computer vision models by formalizing the inductive biases and then integrating them into a unified system with the use of the concepts of Causality and Geometric Deep Learning and inspirations from cognitive science.

In particular, my long-term goal is to address the challenges of learning invariances and discrete abstractions from data, from a theoretical perspective. Geometric deep learning is crucial in this regard, as it enables us to leverage data with inherent relationships, connections, and shared properties, such as graph-structured data (e.g. point clouds in 3D). This approach can improve the generalization of computer vision systems, as well as provide insights into the underlying mechanisms of perception and cognition and it has the potential to unlock new insights and enable more sophisticated and accurate models.

:page_with_curl: Download my resumé.

Education

  • PhD: Machine Learning - Georgia Institute of Technology - 2022-Present
  • BSc: Electrical-Electronics Engineering - Bogazici University - 2018-2022
  • High School: Math and Science - Kadikoy Anadolu High School - 2013-2018

Research Experience

Professional Experience

news

Apr 22, 2023 I will be serving as a mentor in Google Summer of Code 2023 program this summer. You can find the details of our projects at the following link: GitHub
Apr 29, 2022 I have been accepted at the Machine Learning PhD program at Georgia Tech, starting Fall’22.
Apr 22, 2022 I will be interning at VILAB-EPFL under Dr. Amir Zamir for 2022 Summer.
Mar 2, 2022 First ‘First Author’ paper on computer vision was accepted to CVPR 2022.

selected publications

  1. cvpr_isnasdip.JPG
    ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior
    Metin Ersin* Arican, Ozgur Kara*, Gustav Bredell, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2022
    PDF Code
  2. ieee_ac.JPG
    Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
    Nikhil Churamani, Ozgur Kara, and Hatice Gunes
    IEEE Transactions on Affective Computing, Jun 2022
    PDF Code
  3. nanocom.jpg
    Molecular index modulation using convolutional neural networks
    Ozgur Kara, Gokberk Yaylali, Ali Emre Pusane, and 1 more author
    Nano Communication Networks, Dec 2022
    PDF Code
  4. leap_hri.JPG
    Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition
    Ozgur Kara, Nikhil Churamani, and Hatice Gunes
    In Workshop on Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI), 16th ACM/IEEE International Conference on Human-Robot Interaction (HRI), Dec 2021
    PDF Code
  5. neuroweaver.JPG
    Neuroweaver: a platform for designing intelligent closed-loop neuromodulation systems
    Parisa Sarikhani, Hao-Lun Hsu, Ozgur Kara, and 3 more authors
    Brain Stimulation: Basic, Translational, and Clinical Research in Neuromodulation, Dec 2021
    PDF Code