20 citations · 28 across the 6 of their papers we have counts for
7 papers
Efficient Credal Prediction through Decalibration
Paul Hofman, Timo Löhr, Maximilian Muschalik +2
A reliable representation of uncertainty is essential for the application of modern machine learning methods in safety-critical settings. In this regard, the use of credal sets (i.…
Credal Prediction based on Relative Likelihood
Timo Löhr, Paul Hofman, Felix Mohr +1
Predictions in the form of sets of probability distributions, so-called credal sets, provide a suitable means to represent a learner's epistemic uncertainty. In this paper, we prop…
Label-wise Aleatoric and Epistemic Uncertainty Quantification
Yusuf Sale, Paul Hofman, Timo Löhr +3
We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows unce…
Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images
Chinmay Prabhakar, Hongwei Bran Li, Johannes C. Paetzold +6
Multiple Sclerosis (MS) is a severe neurological disease characterized by inflammatory lesions in the central nervous system. Hence, predicting inflammatory disease activity is cru…
blob loss: instance imbalance aware loss functions for semantic segmentation
Florian Kofler, Suprosanna Shit, Ivan Ezhov +14
Deep convolutional neural networks (CNN) have proven to be remarkably effective in semantic segmentation tasks. Most popular loss functions were introduced targeting improved volum…
FedCostWAvg: A new averaging for better Federated Learning
Leon Mächler, Ivan Ezhov, Florian Kofler +5
We propose a simple new aggregation strategy for federated learning that won the MICCAI Federated Tumor Segmentation Challenge 2021 (FETS), the first ever challenge on Federated Le…
Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns
Hongwei Li, Timo Loehr, Anjany Sekuboyina +3
In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying…