Francesco Di Salvo

According to our database, Francesco Di Salvo authored at least 11 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis.

Francesco Di Salvo, Sebastian Doerrich, Jonas Alle, Christian Ledig

Trans. Mach. Learn. Res., 2026

Stylizing ViT: Anatomy-Preserving Instance Style Transfer for Domain Generalization.

Sebastian Doerrich, Francesco Di Salvo, Jonas Alle, Christian Ledig

Proceedings of the 23rd IEEE International Symposium on Biomedical Imaging, 2026

2025

An Embedding is Worth a Thousand Noisy Labels.

Francesco Di Salvo, Sebastian Doerrich, Ines Rieger, Christian Ledig

Trans. Mach. Learn. Res., 2025

Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs.

Francesco Di Salvo, Hanh Huyen My Nguyen, Christian Ledig

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2025, 2025

2024

MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions.

Francesco Di Salvo, Sebastian Doerrich, Christian Ledig

CoRR, 2024

Rethinking Model Prototyping through the MedMNIST+ Dataset Collection.

Sebastian Doerrich, Francesco Di Salvo, Julius Brockmann, Christian Ledig

CoRR, 2024

Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization.

Sebastian Doerrich, Francesco Di Salvo, Christian Ledig

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2024, 2024

Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification.

Sebastian Doerrich, Tobias Archut, Francesco Di Salvo, Christian Ledig

Proceedings of the IEEE International Symposium on Biomedical Imaging, 2024

Privacy-preserving datasets by capturing feature distributions with Conditional VAEs.

Francesco Di Salvo, David Tafler, Sebastian Doerrich, Christian Ledig

Proceedings of the 35th British Machine Vision Conference, 2024

Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations.

Sebastian Doerrich, Francesco Di Salvo, Christian Ledig

Proceedings of the 35th British Machine Vision Conference Workshop Proceedings, 2024

2023

unORANIC: Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features.

Sebastian Doerrich, Francesco Di Salvo, Christian Ledig

Proceedings of the Machine Learning in Medical Imaging - 14th International Workshop, 2023