Saved in:
Bibliographic Details
Main Authors: Vardi, Ben, Schonberger, Dana, Friedmann, Yuval, Yakhini, Zohar, Barshack, Iris, Loebel, Alexander, Shamir, Ariel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.25175
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911714545500160
author Vardi, Ben
Schonberger, Dana
Friedmann, Yuval
Yakhini, Zohar
Barshack, Iris
Loebel, Alexander
Shamir, Ariel
author_facet Vardi, Ben
Schonberger, Dana
Friedmann, Yuval
Yakhini, Zohar
Barshack, Iris
Loebel, Alexander
Shamir, Ariel
contents Pathology foundation models (PFMs) have advanced rapidly in recent years and support training classifiers for a range of histopathology tasks. However, their robustness across hospitals remains limited: performance often degrades when training a classifier on data from one hospital and evaluating it on another target hospital. We address this challenge by fine-tuning PFMs with a local maximum mean discrepancy (LMMD) objective that applies to two settings: domain adaptation, where unlabeled target-hospital data is available, and domain generalization, where target-hospital data is unavailable at all. Experiments at both the patch- and slide-level show consistent improvements across multiple PFMs and tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25175
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Discrepancy Minimization Improves Cross-Hospital Robustness in Digital Pathology
Vardi, Ben
Schonberger, Dana
Friedmann, Yuval
Yakhini, Zohar
Barshack, Iris
Loebel, Alexander
Shamir, Ariel
Computer Vision and Pattern Recognition
Pathology foundation models (PFMs) have advanced rapidly in recent years and support training classifiers for a range of histopathology tasks. However, their robustness across hospitals remains limited: performance often degrades when training a classifier on data from one hospital and evaluating it on another target hospital. We address this challenge by fine-tuning PFMs with a local maximum mean discrepancy (LMMD) objective that applies to two settings: domain adaptation, where unlabeled target-hospital data is available, and domain generalization, where target-hospital data is unavailable at all. Experiments at both the patch- and slide-level show consistent improvements across multiple PFMs and tasks.
title Discrepancy Minimization Improves Cross-Hospital Robustness in Digital Pathology
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.25175