Answers are grounded in this paper and cite their sources.
Infrared (IR) ship semantic segmentation is pivotal for all-weather maritime surveillance and national early-warning applications. However, the significant domain gap between IR and visible 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 class-specific adapters and segment anything model (SAM) refinement Network is proposed for cross-domain few-shot IR 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 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 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 of 63.19%, exceeding the second-best method by 4.43%, thereby validating its effectiveness.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: