← Search

Eike Petersen

2 accepted papers

2024

Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation

ECCV 2024oral

"Shortcut learning is when a model – e.g. a cardiac disease classifier – exploits correlations between the target label and a spurious shortcut feature, e.g. a pacemaker, to predict the target label based on the shortcut rather than real discriminative features. This is common in medical imaging, wh…

2023

That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation

ICLR 2023poster

Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in the way they are generated, for example through the use of dif…

Cited by 10SourcePDFScholar