Zhang, Ting, Liu, Pengyi, Liu, Zhaoyinγ, Chen, Yingchun, Alfuhaid, Hisham, Al-Antary, Mohammad, Waqas, Muhammad ORCID: https://orcid.org/0000-0003-0814-7544 and Hussain, Syed Mudassir (2026) Cross-domain few-shot infrared ship segmentation with class-specific adapters and SAM refinement. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. ISSN 1939-1404 (Print), 2151-1535 (Online) (doi:10.1109/JSTARS.2026.3704472)

Preview

PDF (Author's Accepted Manuscript) 53799 WAQAS_Cross-Domain_Few-Shot_Infrared_Ship_Segmentation_(AAM)_2026.pdf - Accepted Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Infrared ship semantic segmentation is pivotal for all-weather maritime surveillance and national early-warning applications. However, the significant domain gap between infrared (IR) and visible (VIS) images, combined with the extreme scarcity of annotated samples in the target IR domain, poses a dual challenge that severely restricts the cross-domain application of segmentation networks. Existing few-shot segmentation methods mostly assume similar data distributions, while domain adaptation methods rely on abundant unlabeled data; consequently, neither approach effectively addresses the combined problem of cross-domain and few-shot learning. To address this issue, a two-stage framework named CAS-Net (Class-specific Adapters and SAM refinement Network) is proposed for cross-domain few-shot infrared ship semantic segmentation. The framework first learns domain-invariant features and then leverages a handful of annotated IR samples for class-specific adaptation and mask refinement. Specifically, in the first stage, a dual-branch network integrating wavelet transform and convolution is designed to extract robust cross-domain features, employing a random convolution perturbation (RCP) strategy to stabilize adversarial training. In the second stage, independent, lightweight class-specific adapters are introduced for each target class and efficiently fine-tuned via self-supervised contrastive learning. Furthermore, the Segment Anything Model (SAM) is incorporated during inference through a prototype-driven prompt generation mechanism to refine initial segmentation results and enhance boundary accuracy. Experimental results on the VI-Ship and Agriculture-Vision datasets demonstrate that the proposed method outperforms state-of-the-art approaches across multiple evaluation metrics. Notably, under the extreme one-shot setting on the VI-Ship dataset, the proposed method achieves a mean Intersection over Union (mIoU) of 63.19%, exceeding the second-best method by 4.43%, there.

Item Type:	Article
Uncontrolled Keywords:	gross-domain few-shot learning, infrared ship imagery, class-specific adapters, Segment Anything Model (SAM), prototype learning.
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General)
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified:	22 Jun 2026 10:17
URI:	https://gala.gre.ac.uk/id/eprint/53799

Actions (login required)

View Item

Downloads