Deep Learning

Learning discriminative powerful representations is a crucial step for machine learning systems. Introducing invariance against arbitrary nuisance or sensitive attributes while performing well on specific tasks is an important problem in …

This 5 years Helmholtz funded project to advance the field with Federated Learning algorithms in Medicine (2020-2025)

This 5 years Helmholtz funded project to advance the field with Federated Learning algorithms in Medicine (2020-2025)

Crowdsourcing, Gamification

Manifold Learning, Graph Convolutional Networks

Domain Adaptation, Style Transfer

Meta-Learning, Few-Shot Learning

Interpretable ML, Disentangled Representation, Fairness

Detection, Classification, Segmentation, Anomaly Detection, Semi-/Weakly-Supervised Learning

DAAD Funded Project with ETH Zürich and Imperial College London (2020-2022)