Search Results for author:
Found 3 papers, 2 papers with code
Mitigating attribute amplification in counterfactual image generation
Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries.
Distance Matters For Improving Performance Estimation Under Covariate Shift
In this work, we show that taking into account distances of test samples to their expected training distribution can significantly improve performance estimation under covariate shift.
The Role of Subgroup Separability in Group-Fair Medical Image Classification
We investigate performance disparities in deep classifiers.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
