Fairness by Learning Orthogonal Disentangled Representations
16th European Conference on Computer Vision (ECCV), 2020
Alumni
Hasan Sarhan
PhD (TU Munich, 2024)
Now: Senior Data Scientist, Johnson & Johnson
Technical University of Munich
Hasan Sarhan did his PhD at the Technical University of Munich (2024), co-supervised in our group, on representation learning and fair AI for medical imaging. His work covered disentangled representations with adversarial VAEs, fairness through orthogonal disentangled representations (ECCV 2020), and microaneurysm segmentation for diabetic retinopathy screening. He is now a Senior Data Scientist at Johnson & Johnson, working on AI for surgery, and is committed to sharing AI and data-science knowledge with middle-income countries.
Education
- 2024PhD in Computer ScienceTechnical University of Munich
- 2016M.Sc.Technical University of Munich
Publications 4 filter all →
Learning interpretable disentangled representations using adversarial vaes
Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data, 2019
Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss
International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019