12 citations · 15 across the 15 of their papers we have counts for
16 papers
Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching
Sebastian Doerrich, Francesco Di Salvo, Shyam Nandan Rai +2
Hardware shifts, color variations, and changing patient characteristics between development and deployment routinely break trained medical image classifiers. Existing remedies fall…
Layer Selection in VLMs for Zero-Shot OOD Detection via Multi-Resolution Entropy Estimation
Shyam Nandan Rai, Francesco Di Salvo, Sebastian Doerrich +1
Out-of-distribution (OOD) detection is crucial for safe deployment of medical AI systems, where domain shifts arise across institutions, acquisition protocols, and patient populati…
TRUE-Colon: Exposing a Consistent Transfer Asymmetry in Real-Time Polyp Detection
Sebastian Doerrich, Andreas Franz Schwab, Francesco Di Salvo +3
Computer-aided detection (CADe) systems for colonoscopy promise to reduce clinical miss rates, yet reliable real-world deployment remains elusive. This translational gap stems in p…
MoPET: Parameter-Efficient Mixture-of-Experts for Unified Medical Image Classification
Sebastian Doerrich, Daniel Würtinger, Francesco Di Salvo +2
Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end…
Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi +4
Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is conside…
MaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring
Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
Foundation models provide highly descriptive representations for medical images, yet their reliability degrades under distribution shifts arising from changes in patients, devices,…
HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis
Francesco Di Salvo, Sebastian Doerrich, Jonas Alle +1
Robust generalization beyond training distributions remains a critical challenge for deep neural networks. This is especially pronounced in medical image analysis, where data is of…
Stylizing ViT: Anatomy-Preserving Instance Style Transfer for Domain Generalization
Sebastian Doerrich, Francesco Di Salvo, Jonas Alle +1
Deep learning models in medical image analysis often struggle with generalizability across domains and demographic groups due to data heterogeneity and scarcity. Traditional augmen…
Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs
Francesco Di Salvo, Hanh Huyen My Nguyen, Christian Ledig
Deep Learning (DL) has revolutionized medical imaging, yet its adoption is constrained by data scarcity and privacy regulations, limiting access to diverse datasets. Federated Lear…
Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations
Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
This study introduces unORANIC+, a novel method that integrates unsupervised feature orthogonalization with the ability of a Vision Transformer to capture both local and global rel…
An Embedding is Worth a Thousand Noisy Labels
Francesco Di Salvo, Sebastian Doerrich, Ines Rieger +1
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust a…
Privacy-preserving datasets by capturing feature distributions with Conditional VAEs
Francesco Di Salvo, David Tafler, Sebastian Doerrich +1
Large and well-annotated datasets are essential for advancing deep learning applications, however often costly or impossible to obtain by a single entity. In many areas, including…
MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions
Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community estab…
Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization
Sebastian Doerrich, Francesco Di Salvo, Christian Ledig
Despite notable advancements, the integration of deep learning (DL) techniques into impactful clinical applications, particularly in the realm of digital histopathology, has been h…
Rethinking model prototyping through the MedMNIST+ dataset collection
Sebastian Doerrich, Francesco Di Salvo, Julius Brockmann +1
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has…
Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification
Sebastian Doerrich, Tobias Archut, Francesco Di Salvo +1
Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes. Yet, this adaptability is vital for addressing user da…