Ashkan Khakzar

Researcher in Machine Learning and Computer Vision

prof_pic.jpg

I’m a postdoctoral researcher in machine learning at the Torr vision group (Philip Torr) at the University of Oxford (since March 2023), focusing on explainable and robust machine learning. Previously I was a doctoral candidate at the Technical University of Munich (TUM), where I worked on neural network explanation. My thesis referees were Prof. Bernt Schiele and Prof. Nassir Navab. Throughout my journey, I’ve had the opportunity to work on a wide range of fascinating topics in computer vision, deep learning, and their medical applications with Nassir Navab and Daniel Rueckert (TUM). Still lucky to be an affiliate researcher at the Munich Center for Machine Learning (MCML). When I’m not working on research, I love exploring the great outdoors.

selected publications

  1. CVPR
    Do explanations explain? model knows best
    Ashkan Khakzar, Pedram Khorsandi, Rozhin Nobahari, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
    HTML Code
  2. CVPR
    Neural Response Interpretation through the Lens of Critical Pathways
    Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, and 3 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021
    HTML Code Website
  3. NeurIPS
    Fine-grained neural network explanation by identifying input features with predictive information
    Yang Zhang*, Ashkan Khakzar*, Yawei Li, and 3 more authors
    Advances in Neural Information Processing Systems, 2021
    HTML Code Website
  4. MICCAI
    Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models
    Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger, and 5 more authors
    In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, 2021
    arXiv HTML Code