3 papers
cs.CV2026
Towards Interpretable Foundation Models for Retinal Fundus Images
Samuel Ofosu Mensah, Camila Roa, Kerol Djoumessi +1
Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models…
cs.LG2025
Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning
Samuel Ofosu Mensah, Kerol Djoumessi, Philipp Berens
Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources while maintaining privacy. Nevertheless,…
cs.CV2025
A Hybrid Fully Convolutional CNN-Transformer Model for Inherently Interpretable Disease Detection from Retinal Fundus Images
Kerol Djoumessi, Samuel Ofosu Mensah, Philipp Berens
In many medical imaging tasks, convolutional neural networks (CNNs) efficiently extract local features hierarchically. More recently, vision transformers (ViTs) have gained popular…