PhD Student and Researcher · Computer Vision
I develop computer vision systems that remain reliable when data is limited, synthetic, or shifted.
One question. Three connected directions.
How can a model generalize responsibly when the real world does not match its training set?
Research imagery is conceptual, not experimental output.
Medical image analysis
Brain MRI segmentation across high- and low-quality imaging domains.
Beyond clean benchmarks
I explore transfer learning, ensemble models, and conformal risk control to study reliability under domain shift.
Facial analysis & synthetic data
Understanding expressions through real and synthetic visual data.
Learning from generated data
Privacy-aware facial expression recognition and text-guided expression generation using vision-language and generative models, synthetic data, and cross-dataset evaluation.
Multimodal visual understanding
Connecting what a model sees with what language means.
Visual + language
Vision-language models and visual-textual cross-attention for multimodal reasoning, including IMMCAN idiom understanding and open-world text-guided visual counting.
Selected publications
Peer-reviewed work and open research across medical vision, facial analysis, multimodal reasoning, and visual counting.
22nd Workshop on Multiword Expressions · ACL, 2026 · pp. 149–153
Integrates visual and textual representations through multimodal cross-attention for idiom understanding and multimodal reasoning.
IEEE FG 2026 · Kyoto, Japan · First author
Examines pseudo-labeling, diffusion-based synthesis, and GAN-based expression editing as privacy-preserving ways to address imbalance and limited facial-expression data.
MICCAI 2025 BraTS-Lighthouse · LNCS 16376 · Springer, 2026
Combines GLIMS and MedNeXt with transfer learning and ensemble fusion to improve brain-tumor segmentation under low-quality imaging conditions.
Computer Vision and Image Understanding · 2026 · Article 104703
Introduces a taxonomy spanning reference-based, reference-less, and open-world text-guided counting, and reviews 29 approaches on established benchmarks.
Behind the research
I am a PhD student in Computer Engineering at Istanbul Technical University and a Graduate Research Assistant at SiMiT Lab, working under the supervision of Prof. Dr. Hazım Kemal Ekenel.
My research sits at the intersection of computer vision, deep learning, and trustworthy AI. I study how vision models behave beyond clean benchmarks: under domain shift, limited annotations, low-quality medical scans, privacy constraints, and imbalanced data.
Current directions include reliable brain-tumor MRI segmentation, conformal risk control, vision-language-guided facial expression generation, multimodal idiom understanding, and class-agnostic visual counting.
I am enthusiastic about exploring emerging ideas, continuously expanding my knowledge, and applying what I learn to solve challenging real-world problems.
Research & education
Istanbul Technical University · Computer vision and trustworthy medical AI
Istanbul Technical University · Research and undergraduate teaching
SiMiT Lab, ITU · Computer vision, biometrics, and medical imaging
Istanbul Technical University
University of Tabriz
Research collaboration
For research discussions, collaborations, or questions about my published work, reach me through my ITU email.
Start a conversation