Saved in:
Bibliographic Details
Main Authors: Talks, Joshua, Marchesini, Kevin, Lumetti, Luca, Bolelli, Federico, Kreshuk, Anna
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.00450
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913014054125568
author Talks, Joshua
Marchesini, Kevin
Lumetti, Luca
Bolelli, Federico
Kreshuk, Anna
author_facet Talks, Joshua
Marchesini, Kevin
Lumetti, Luca
Bolelli, Federico
Kreshuk, Anna
contents Model reuse offers a solution to the challenges of segmentation in biomedical imaging, where high data annotation costs remain a major bottleneck for deep learning. However, although many pretrained models are released through challenges, model zoos, and repositories, selecting the most suitable model for a new dataset remains difficult due to the lack of reliable model ranking methods. We introduce the first black-box-compatible framework for unsupervised and source-free ranking of semantic and instance segmentation models based on the consistency of predictions under perturbations. While ranking methods have been studied for classification and a few segmentation-related approaches exist, most target related tasks such as transferability estimation or model validation and typically rely on labelled data, feature-space access, or specific training assumptions. In contrast, our method directly addresses the repository setting and applies to both semantic and instance segmentation, for zero-shot reuse or after unsupervised domain adaptation. We evaluate the approach across a wide range of biomedical segmentation tasks in both 2D and 3D imaging, showing that our estimated rankings strongly correlate with true target-domain model performance rankings.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00450
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift
Talks, Joshua
Marchesini, Kevin
Lumetti, Luca
Bolelli, Federico
Kreshuk, Anna
Computer Vision and Pattern Recognition
Model reuse offers a solution to the challenges of segmentation in biomedical imaging, where high data annotation costs remain a major bottleneck for deep learning. However, although many pretrained models are released through challenges, model zoos, and repositories, selecting the most suitable model for a new dataset remains difficult due to the lack of reliable model ranking methods. We introduce the first black-box-compatible framework for unsupervised and source-free ranking of semantic and instance segmentation models based on the consistency of predictions under perturbations. While ranking methods have been studied for classification and a few segmentation-related approaches exist, most target related tasks such as transferability estimation or model validation and typically rely on labelled data, feature-space access, or specific training assumptions. In contrast, our method directly addresses the repository setting and applies to both semantic and instance segmentation, for zero-shot reuse or after unsupervised domain adaptation. We evaluate the approach across a wide range of biomedical segmentation tasks in both 2D and 3D imaging, showing that our estimated rankings strongly correlate with true target-domain model performance rankings.
title Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shift
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.00450