Salma Haidar, PhD, CFA

About Me

I earned my PhD at the University of Antwerp (imec-IDLab), where I worked at the intersection of hyperspectral imaging and deep learning. My research focuses on data-efficient representation learning and using post-hoc explainability to analyse model behaviour and support spectral dimensionality reduction—aiming for methods that remain reliable beyond controlled settings. My doctoral thesis spans (i) patch-level, multi-label classification for mixed-material regions, (ii) self-supervised contrastive learning under label scarcity, and (iii) explainability-driven band selection for more compact, wavelength aware inputs.

I enjoy turning principled ideas into practical tools that hold up across domains. In practice, this often means pre-training on unlabelled data, followed by fine-tuning robust predictors with limited annotations, and utilising explanation signals to prioritise informative wavelengths while aiming to preserve predictive performance. I’m especially interested in evaluation beyond headline accuracy—stability, uncertainty, and whether explanations are both model aligned and meaningful in the application domain.

Before moving into AI, I completed an MSc in Money & Banking at the American University of Beirut and worked in international banking. As a CFA charterholder, I bring rigour, risk thinking, and an eye for operational constraints to model design and validation. That background shapes how I prioritise reproducibility, clarity, and decision-usefulness in research.

Recent outputs include a journal article on training strategies for multi-label hyperspectral classifiers, contrastive learning for multi-label prediction, contrastive learning in low-label regimes, and explainability-guided band selection. I also review for IEEE TGRS and have supervised BSc and MSc projects at the University of Antwerp.

Outside research, I keep up with new developments in AI and machine learning—and I enjoy the ongoing debates around their real-world impact and ethical implications.

Research Interests

• Artificial Intelligence
• Machine Learning
• Hyperspectral Image Analysis
• Computer Vision
• Explainable and Reliable ML
• Data Science

Hobbies

• Reading
• Photography
• Walking
• Hiking
• Travelling
• Bread baking