PhD in Electrical and Computer Engineering, Technion
My research focuses on Computer Vision and Deep Learning, with an emphasis on understanding and modeling the relationship between visual data and high-level semantic structure. I am particularly interested in developing methods for capturing rare phenomena and uncovering meaningful structure in complex visual data.
My work includes:
-
GAN-based image domain transfer, focusing on learning mappings between visual domains and capturing cross-domain correspondences — project page
-
Anomaly detection, where I study methods for identifying rare and unexpected patterns in high-dimensional visual data:
- k-NNN — a framework for scalable and effective anomaly detection based on nearest-neighbor structures (GitHub)
-
Concept retrieval, focusing on uncovering and querying latent semantic concepts:
- coret — a surrogate-based approach for concept retrieval in complex visual representations (GitHub)
More broadly, my research lies at the intersection of representation learning, rare event modeling, and semantic interpretability in visual systems.