Dzemail Rozajac
Papers
1
Total Citations
4
H-Index
1
About
Džemail Rožajac is a researcher at the forefront of explainable artificial intelligence (XAI), with a particular focus on making deep learning models interpretable for safety-critical applications. His primary research areas include 3D semantic segmentation, generative AI, and counterfactual explanations for point cloud data. Rožajac’s most notable contribution is his pioneering work on generating counterfactual explanations for 3D semantic segmentation models—a domain where traditional interpretability methods falter due to the sparsity and unordered nature of point cloud data. By leveraging generative AI, he has developed techniques that produce meaningful, human-understandable counterfactuals, enabling researchers and engineers to better understand model predictions in autonomous driving, robotics, and geospatial analysis. His 2025 paper on this topic has already garnered 4 citations, signaling its growing influence in the XAI community. Rožajac’s work bridges a critical gap between complex 3D perception models and the need for transparency, making him a key voice in the push toward trustworthy AI in high-stakes environments.
Research Focus
Key Achievements
Top Papers
- 1