Semantic-Aware Ship Detection with Vision-Language Integration
This work addresses ship detection for applications like maritime monitoring and logistics, but it appears incremental as it builds on existing VLMs with a new dataset and strategy.
The paper tackles ship detection in remote sensing imagery by proposing a novel framework that integrates Vision-Language Models with a multi-scale adaptive sliding window strategy, and introduces ShipSem-VL, a specialized dataset for fine-grained ship attributes, demonstrating effectiveness across three evaluation tasks.
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.