Exploiting independent query information for few-shot image segmentation

Liu, Weide, Wu, Zhonghua, Ding, Henghui, Liu, Fayao, Lin, Jie, Lin, Guosheng and Zhou, Wei 2026. Exploiting independent query information for few-shot image segmentation. Displays 91 , 103179. 10.1016/j.displa.2025.103179

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (3MB) | Preview

Abstract

This work addresses the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query image segmentation. Although some works propose to build a cross-reference between support and query images, their extraction of query information still depends on the support images. In this paper, we propose to extract the information from the query itself independently to benefit the few-shot segmentation task. To this end, we first propose a prior extractor to learn the query information from the unlabeled images with our proposed global–local contrastive learning. Then, we extract a set of predetermined priors via this prior extractor. With the obtained priors, we generate the prior region maps for query images, which locate the objects, as guidance to perform cross-interaction with support features. In such a way, the extraction of query information is detached from the support branch, overcoming the limitation by support, and could obtain more informative query clues to achieve better interaction. Without bells and whistles, the proposed approach achieves new state-of-the-art performance for the few-shot segmentation task on public datasets.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	Elsevier
ISSN:	0141-9382
Date of First Compliant Deposit:	12 December 2025
Date of Acceptance:	6 August 2025
Last Modified:	12 Dec 2025 17:07
URI:	https://orca.cardiff.ac.uk/id/eprint/183208

Actions (repository staff only)

Edit Item