2 papers
eess.IV2026
Useful nonrobust features are ubiquitous in biomedical images
Coenraad Mouton, Randle Rabe, Niklas C. Koser +4
We study whether deep networks for medical imaging learn useful nonrobust features - predictive input patterns that are not human interpretable and highly susceptible to small adve…
cs.CV2024
Real-World Federated Learning in Radiology: Hurdles to overcome and Benefits to gain
Markus R. Bujotzek, Ünal Akünal, Stefan Denner +17
Objective: Federated Learning (FL) enables collaborative model training while keeping data locally. Currently, most FL studies in radiology are conducted in simulated environments…