Quantifying epistemic uncertainty in deep learning
Uncertainty quantification is at the core of the reliability and robustness of machine learning.
In this paper, we provide a theoretical framework to dissect the uncertainty, especially …
In this paper, we provide a theoretical framework to dissect the uncertainty, especially …
Modality redundancy for MRI-based glioblastoma segmentation
S De Sutter, J Wuts, W Geens, AM Vanbinst… - International journal of …, 2024 - Springer
Purpose Automated glioblastoma segmentation from magnetic resonance imaging is
generally performed on a four-modality input, including T1, contrast T1, T2 and FLAIR. We …
generally performed on a four-modality input, including T1, contrast T1, T2 and FLAIR. We …
On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
M Fellaji, F Pennerath, B Conan-Guez… - … European Conference on …, 2024 - Springer
The calibration of predictive distributions has been widely studied in deep learning, but the
same cannot be said about the more specific epistemic uncertainty as produced by Deep …
same cannot be said about the more specific epistemic uncertainty as produced by Deep …