collaborators

7 papers

cs.CV2025

Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis

Tian Xia, Matthew Sinclair, Andreas Schuh +8

Counterfactual image generation is a powerful tool for augmenting training data, de-biasing datasets, and modeling disease. Current approaches rely on external classifiers or regre…

cs.LG2025

A Primer on Causal and Statistical Dataset Biases for Fair and Robust Image Analysis

Charles Jones, Ben Glocker

Machine learning methods often fail when deployed in the real world. Worse still, they fail in high-stakes situations and across socially sensitive lines. These issues have a chill…

cs.CV2025

Exploring the interplay of label bias with subgroup size and separability: A case study in mammographic density classification

Emma A. M. Stanley, Raghav Mehta, Mélanie Roschewitz +2

Systematic mislabelling affecting specific subgroups (i.e., label bias) in medical imaging datasets represents an understudied issue concerning the fairness of medical AI systems.…

cs.CV2025

Where are we with calibration under dataset shift in image classification?

Mélanie Roschewitz, Raghav Mehta, Fabio de Sousa Ribeiro +1

We conduct an extensive study on the state of calibration under real-world dataset shift for image classification. Our work provides important insights on the choice of post-hoc an…

eess.IV2025

CF-Seg: Counterfactuals meet Segmentation

Raghav Mehta, Fabio De Sousa Ribeiro, Tian Xia +4

Segmenting anatomical structures in medical images plays an important role in the quantitative assessment of various diseases. However, accurate segmentation becomes significantly…

cs.LG2025

Subgroups Matter for Robust Bias Mitigation

Anissa Alloula, Charles Jones, Ben Glocker +1

Despite the constant development of new bias mitigation methods for machine learning, no method consistently succeeds, and a fundamental question remains unanswered: when and why d…