ORIGINAL RESEARCH article
Front. Remote Sens.
Sec. Image Analysis and Classification
Volume 6 - 2025 | doi: 10.3389/frsen.2025.1662024
This article is part of the Research TopicMachine Learning for Advanced Remote Sensing: From Theory to Applications and Societal ImpactView all articles
CARP: Cloud-Adaptive Robust Prompting of Vision-Language Models for Ship Classification under Cloud Occlusion
Provisionally accepted
- Naval University of Engineering, Wuhan, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Fine-grained few-shot ship classification under cloud occlusion is vital for maritime safety but remains challenging due to corrupted features and limited data utility.While the advent of large pre-trained vision-language models(VLMs) provides promising solutions, the lack of specialized benchmarks hinders their effective application. To address this, we introduce SeaCloud-Ship, the first benchmark dedicated to this task. It comprises 7,654 highresolution, high-quality annotated images across 30 classes, featuring quantified cloud coverage (12.5% to 75%) for standardized evaluation. We innovatively propose CARP, a cloudaware prompting framework built upon CoOp, to combat feature corruption, semantic misalignment, and utility decay. Our core contributions include: ( 1) GCE Loss dynamically adjusting classification weights to suppress cloud interference based on feature degradation severity; (2) Adaptive Optimization Prompt Design (AOPD) utilizing distortion-aware vectors for effective multi-modal feature alignment and semantic deviation repair; (3) Dynamic Weight Adjustment Mechanism (DWAM) real-time balancing of multi-source feature fusion by evaluating inter-modal information gain. Extensive experiments on SeaCloud-Ship demonstrate CARP's superior robustness and state-of-theart performance, establishing a strong baseline for cloud-occluded ship classification.
Keywords: Remote sensing ship classification, vision-language models, Few-shot learning, cloud occlusion, prompt tuning Cloud-Adaptive Robust Prompting of Vision-Language Models for Ship Classification under Cloud Occlusion 11
Received: 08 Jul 2025; Accepted: 11 Aug 2025.
Copyright: © 2025 Zhan, Song, Huang, Tan and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Yiping Song, Naval University of Engineering, Wuhan, China
Xun Huang, Naval University of Engineering, Wuhan, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.