activity
20182026
most citedBounding boxes for weakly supervised segmentation: Global constraints get close to full supervision

17 citations · 19 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2026

Prompting with the human-touch: evaluating model-sensitivity of foundation models for musculoskeletal CT segmentation

Caroline Magg, Maaike A. ter Wee, Johannes G. G. Dobbe +4

Promptable Foundation Models (FMs), initially introduced for natural image segmentation, have also revolutionized medical image segmentation. The increasing number of models, along…

cs.CV2025

In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging

Valentina Corbetta, Floris Six Dijkstra, Regina Beets-Tan +3

Deep learning models in medical imaging often achieve strong in-distribution performance but struggle to generalise under distribution shifts, frequently relying on spurious correl…

cs.CV2024

Zero-shot capability of SAM-family models for bone segmentation in CT scans

Caroline Magg, Hoel Kervadec, Clara I. Sánchez

The Segment Anything Model (SAM) and similar models build a family of promptable foundation models (FMs) for image and video segmentation. The object of interest is identified usin…

cs.CV2023

Leveraging point annotations in segmentation learning with boundary loss

Eva Breznik, Hoel Kervadec, Filip Malmberg +4

This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design the boundary loss imposes a strong…

cs.CV2023

On the dice loss gradient and the ways to mimic it

Hoel Kervadec, Marleen de Bruijne

In the past few years, in the context of fully-supervised semantic segmentation, several losses -- such as cross-entropy and dice -- have emerged as de facto standards to supervise…

cs.CV2021

Beyond pixel-wise supervision for segmentation: A few global shape descriptors might be surprisingly good!

Hoel Kervadec, Houda Bahig, Laurent Letourneau-Guillon +2

Standard losses for training deep segmentation networks could be seen as individual classifications of pixels, instead of supervising the global shape of the predicted segmentation…