Home
Login
Deutsch
Advanced Search
Browse by ...
Publication overview
Contact persons
Help
DOI
 |
|
as soon as is submitted to ZB.
Leveraging Multi-Rater Annotations to Calibrate Object Detectors in Microscopy Imaging.
In: (23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026, 8-11 April 2026, London). 2026. (Proceedings International Symposium on Biomedical Imaging ; 2026-April)
Deep learning-based object detectors have achieved impressive performance in microscopy imaging, yet their confidence estimates often lack calibration, limiting their reliability for biomedical applications. In this work, we introduce a new approach to improve model calibration by leveraging multi-rater annotations. We propose to train separate models on the annotations from single experts and aggregate their predictions to emulate consensus. This improves upon label sampling strategies, where models are trained on mixed annotations, and offers a more principled way to capture inter-rater variability. Experiments on a colorectal organoid dataset annotated by two experts demonstrate that our rater-specific ensemble strategy improves calibration performance while maintaining comparable detection accuracy. These findings suggest that explicitly modelling rater disagreement can lead to more trustworthy object detectors in biomedical imaging.
Altmetric
Additional Metrics?
Edit extra informations
Login
Publication type
Article: Conference contribution
Keywords
Microscopy Imaging ; Object Detection ; Uncertainty Quantification
ISSN (print) / ISBN
1945-7928
e-ISSN
1945-8452
Conference Title
23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026
Conference Date
8-11 April 2026
Conference Location
London
Quellenangaben
Volume: 2026-April