Mélanie Roschewitz

According to our database, Mélanie Roschewitz authored at least 9 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Automatic dataset shift identification to support root cause analysis of AI performance drift.

Mélanie Roschewitz, Raghav Mehta, Charles Jones, Ben Glocker

CoRR, 2024

Rethinking Fair Representation Learning for Performance-Sensitive Tasks.

Charles Jones, Fabio De Sousa Ribeiro, Mélanie Roschewitz, Daniel C. Castro, Ben Glocker

CoRR, 2024

Radio-opaque artefacts in digital mammography: automatic detection and analysis of downstream effects.

Amelia Schueppert, Ben Glocker, Mélanie Roschewitz

CoRR, 2024

Robust image representations with counterfactual contrastive learning.

Mélanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, Ben Glocker

CoRR, 2024

Mitigating Attribute Amplification in Counterfactual Image Generation.

Tian Xia, Mélanie Roschewitz, Fabio De Sousa Ribeiro, Charles Jones, Ben Glocker

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2024, 2024

Counterfactual Contrastive Learning: Robust Representations via Causal Image Synthesis.

Mélanie Roschewitz, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, Ben Glocker

Proceedings of the Data Engineering in Medical Imaging - Second MICCAI Workshop, 2024

2023

Robust semi-supervised segmentation with timestep ensembling diffusion models.

Margherita Rosnati, Mélanie Roschewitz, Ben Glocker

Proceedings of the Machine Learning for Health, 2023

The Role of Subgroup Separability in Group-Fair Medical Image Classification.

Charles Jones, Mélanie Roschewitz, Ben Glocker

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2023, 2023

Distance Matters For Improving Performance Estimation Under Covariate Shift.

Mélanie Roschewitz, Ben Glocker

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023