Sadaf Gulshad

Sadaf Gulshad is a Postdoctoral Researcher in Machine Learning and Computer Vision at MultixLab, University of Amsterdam. She completed her PhD (2022) in Computer Science at the University of Amsterdam under Prof. Dr. Arnold Smeulders, and holds a Master's degree in Electrical Engineering from KAIST (South Korea, 2017) and a Bachelor's in Electrical and Computer Engineering from COMSATS Institute (Pakistan, 2015).

Research Interests: Sadaf focuses on improving AI transparency and robustness through explainable models. Her work addresses challenges like adversarial examples, medical imaging imperfections, and uncertainty estimation in clinical data. Key contributions include hierarchical prototype explainers (HIPE), transform-augmented networks, and attribute-based reasoning frameworks.

Recent Publications: Her research spans explainable AI (CVPR 2023), robustness (NeurIPS 2021), medical imaging analysis (Medical Physics 2023), and uncertainty estimation (European Heart Journal 2021). She develops methods that bridge human cognition with machine learning explainability.

Teaching & Supervision: Sadaf has served as Teaching Assistant for courses including "Applied Machine Learning" and "Multimedia Analytics" at the University of Amsterdam. She supervised multiple Master's theses on topics like green roof distribution analysis, semantic segmentation, and interpretable representation learning in collaboration with institutions such as UMC Utrecht and VU Medical Center.