activity
20242026
most citedWhere are we with calibration under dataset shift in image classification?

1 citations · 1 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2026

Latent-to-Latent Flow for Volumetric Stochastic Segmentation

Omar Todd, Sooha Kim, Raghav Mehta +5

Uncertainty arising from inter-observer variability in medical image segmentation plays an important role in developing treatment plans. Research in this area is inhibited by the l…

cs.CV2026

Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift

Giang Nguyen, Raghav Mehta, Emma A. M. Stanley +4

Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear. We benchmark 15 foundation-mo…

cs.CV2026

GRC-ProbNet: Uncertainty-aware Feature Extraction for Cardiovascular Disease Classification

Yash Shah, Omar Todd, Philipp Seeböck +3

The automatic detection and classification of cardiovascular disease (CVD) from computed tomography (CT) images plays an important role in clinical practice. Recently, a hybrid pip…

cs.CV2026

Counterfactual Stress Testing for Image Classification Models

Moritz Stammel, Fabio De Sousa Ribeiro, Raghav Mehta +2

Deep learning models in medical imaging often fail when deployed in new clinical environments due to distribution shifts in demographics, scanner hardware, or acquisition protocols…

cs.CV2026

Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis

Tian Xia, Matthew Sinclair, Andreas Schuh +8

Counterfactual image generation enables controlled data augmentation, bias mitigation, and disease modeling. However, existing methods guided by external classifiers or regressors…

cs.CV2026

Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation

Marceau Lafargue-Hauret, Raghav Mehta, Fabio De Sousa Ribeiro +2

Image segmentation relies on large annotated datasets, which are expensive and slow to produce. Silver-standard (AI-generated) labels are easier to obtain, but they risk introducin…