Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wåhlstrand, Victor, Alvén, Jennifer, Häggström, Ida
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910054686392320
author Wåhlstrand, Victor
Alvén, Jennifer
Häggström, Ida
author_facet Wåhlstrand, Victor
Alvén, Jennifer
Häggström, Ida
contents We present a framework to take advantage of existing labels at inference, called \textit{exemplars}, in order to improve the performance of object detection in medical images. The method, \textit{exemplar diffusion}, leverages existing diffusion methods for object detection to enable a training-free approach to adding information of known bounding boxes at test time. We demonstrate that for medical image datasets with clear spatial structure, the method yields an across-the-board increase in average precision and recall, and a robustness to exemplar quality, enabling non-expert annotation. Moreover, we demonstrate how our method may also be used to quantify predictive uncertainty in diffusion detection methods. Source code and data splits openly available online: https://github.com/waahlstrand/ExemplarDiffusion
format Preprint
id arxiv_https___arxiv_org_abs_2603_15267
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels
Wåhlstrand, Victor
Alvén, Jennifer
Häggström, Ida
Computer Vision and Pattern Recognition
We present a framework to take advantage of existing labels at inference, called \textit{exemplars}, in order to improve the performance of object detection in medical images. The method, \textit{exemplar diffusion}, leverages existing diffusion methods for object detection to enable a training-free approach to adding information of known bounding boxes at test time. We demonstrate that for medical image datasets with clear spatial structure, the method yields an across-the-board increase in average precision and recall, and a robustness to exemplar quality, enabling non-expert annotation. Moreover, we demonstrate how our method may also be used to quantify predictive uncertainty in diffusion detection methods. Source code and data splits openly available online: https://github.com/waahlstrand/ExemplarDiffusion
title Exemplar Diffusion: Improving Medical Object Detection with Opportunistic Labels
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15267