Segmetron: sample-efficient model-agnostic semantic segmentation with a trustworthy reject option via PQ learning

Bohoran, TA ORCID: https://orcid.org/0000-0001-8510-579X, Parke, KS, Cowley, A, Gulsin, GS, Yeo, J, Dattani, A, McCann, GP and Giannakidis, A ORCID: https://orcid.org/0000-0001-7403-923X, 2026. Segmetron: sample-efficient model-agnostic semantic segmentation with a trustworthy reject option via PQ learning. Pattern Recognition, 179 (Part C): 113753. ISSN 0031-3203

Preview

Text 2621133_Giannakidis.pdf - Published version Download (2MB) | Preview

Abstract

Semantic segmentation can help gain a deeper understanding of a depicted scene and deliver a variety of transformative technologies. However, its application is limited by the covariate shift and the lack of reliable detection techniques. In this study, we introduce a trustworthy, sample-efficient, distribution-free and model-agnostic hypothesis test, named Segmetron, to detect image-level covariate shift in semantic segmentation. To assess an unlabelled target domain, Segmetron relies on an existing (but random) pre-trained semantic segmentation model and the labelled samples used to train it. The test statistic is based on the sample disagreement rate of two ensemble models trained to disagree with the baseline segmenter on unseen samples from the training and deployment sets, respectively. To obtain theoretical guarantees on unknown arbitrary test distributions, we build on recent work on the PQ learning setting of selective classification and extend it to a different discriminative model (i.e. segmenters). To train the enforced disagreement segmenters of each ensemble, we innovatively propose loss functions (to agree) which are more apropos to the semantic segmentation task and comply with the training of the baseline segmenter. We demonstrate that Segmetron outperforms other state-of-the-art techniques in terms of statistical power on two challenging real-world tasks from the cardiovascular magnetic resonance imaging field, concerned with two or more semantic classes, given access to only one image. This work aligns with “Responsible AI” principles, supporting reliable deployment of AI by enhancing robustness. It can potentially enable the widespread adoption of deep learning semantic segmentation technologies across various fields.

Item Type:	Journal article
Publication Title:	Pattern Recognition
Creators:	Bohoran, T.A., Parke, K.S., Cowley, A., Gulsin, G.S., Yeo, J., Dattani, A., McCann, G.P. and Giannakidis, A.
Publisher:	Elsevier BV
Date:	November 2026
Volume:	179
Number:	Part C
ISSN:	0031-3203
Identifiers:	Number Type 10.1016/j.patcog.2026.113753 DOI S0031320326007181 Publisher Item Identifier 2621133 Other
Rights:	© 2026 The Authors. Published by Elsevier Ltd. This is an open access article distributed under the terms of the Creative Commons CC-BY license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Divisions:	Schools > School of Science and Technology
Record created by:	Melissa Cornwell
Date Added:	27 Apr 2026 14:43
Last Modified:	27 Apr 2026 14:43
URI:	https://irep.ntu.ac.uk/id/eprint/55607

Actions (login required)

Edit View

Statistics

Views

Downloads