Semantic-Aware Ship Detection with Vision-Language Integration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jiahao, Pan, Jiancheng, Sun, Yuze, Huang, Xiaomeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912548414029824
author Li, Jiahao
Pan, Jiancheng
Sun, Yuze
Huang, Xiaomeng
author_facet Li, Jiahao
Pan, Jiancheng
Sun, Yuze
Huang, Xiaomeng
contents Ship detection in remote sensing imagery is a critical task with wide-ranging applications, such as maritime activity monitoring, shipping logistics, and environmental studies. However, existing methods often struggle to capture fine-grained semantic information, limiting their effectiveness in complex scenarios. To address these challenges, we propose a novel detection framework that combines Vision-Language Models (VLMs) with a multi-scale adaptive sliding window strategy. To facilitate Semantic-Aware Ship Detection (SASD), we introduce ShipSem-VL, a specialized Vision-Language dataset designed to capture fine-grained ship attributes. We evaluate our framework through three well-defined tasks, providing a comprehensive analysis of its performance and demonstrating its effectiveness in advancing SASD from multiple perspectives.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15930
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic-Aware Ship Detection with Vision-Language Integration
Li, Jiahao
Pan, Jiancheng
Sun, Yuze
Huang, Xiaomeng
Computer Vision and Pattern Recognition
Ship detection in remote sensing imagery is a critical task with wide-ranging applications, such as maritime activity monitoring, shipping logistics, and environmental studies. However, existing methods often struggle to capture fine-grained semantic information, limiting their effectiveness in complex scenarios. To address these challenges, we propose a novel detection framework that combines Vision-Language Models (VLMs) with a multi-scale adaptive sliding window strategy. To facilitate Semantic-Aware Ship Detection (SASD), we introduce ShipSem-VL, a specialized Vision-Language dataset designed to capture fine-grained ship attributes. We evaluate our framework through three well-defined tasks, providing a comprehensive analysis of its performance and demonstrating its effectiveness in advancing SASD from multiple perspectives.
title Semantic-Aware Ship Detection with Vision-Language Integration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.15930