paper-with-me

홈 › Papers

Leveraging Multi-Rater Annotations to Calibrate Object Detectors in Microscopy Imaging

2026-01-30 · Francesco Campi, Lucrezia Tondo, Ekin Karabati, Johannes Betge, Marie Piraud arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.23007

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning self-calibrated optic disc and cup segmentation from multi-rater annotations

2022-06-10 · Junde Wu, Huihui Fang, Fangxin Shang, Zhaowei Wang 외

The segmentation of optic disc(OD) and optic cup(OC) from fundus images is an important fundamental task for glaucoma diagnosis. In the clinical practice, it is often necessary to collect opinions from multiple experts t…

Segmentation

Multi-Rater Calibrated Segmentation Models

2026-05-04 · Meritxell Riera-Marín, Javier García López, Júlia Rodríguez-Comas, Miguel A. González Ballester 외 arxiv

Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a …

Medical Image Segmentation

Learning Calibrated Medical Image Segmentation via Multi-Rater Agreement Modeling

2021-06-19 · CVPR 2021 1 · Wei Ji, Shuang Yu, Junde Wu, Kai Ma 외

In medical image analysis, it is typical to collect multiple annotations, each from a different clinical expert or rater, in the expectation that possible diagnostic errors could be mitigated. Meanwhile, from the com…

DiagnosticImage SegmentationMedical Image AnalysisMedical Image Segmentation+2

Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raters

2022-12-01 · Junde Wu, Huihui Fang, Yehui Yang, Yuanpei Liu 외

In medical image segmentation, it is often necessary to collect opinions from multiple experts to make the final decision. This clinical routine helps to mitigate individual bias. But when data is multiply annotated, sta…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Labels have Human Values: Value Calibration of Subjective Tasks

2026-01-10 · Mohammed Fayiz Parappan, Ricardo Henao arxiv

Building NLP systems for subjective tasks requires one to ensure their alignment to contrasting human values. We propose the MultiCalibrated Subjective Task Learner framework (MC-STL), which clusters annotations into ide…