4 papers
Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method
Fei Wang, Chengcheng Chen, Hongyu Chen +2
Recently, large language models (LLMs) and vision-language models (VLMs) have achieved significant success, demonstrating remarkable capabilities in understanding various images an…
MID: A Comprehensive Shore-Based Dataset for Multi-Scale Dense Ship Occlusion and Interaction Scenarios
Yugang Chang, Hongyu Chen, Fei Wang +2
This paper introduces the Maritime Ship Navigation Behavior Dataset (MID), designed to address challenges in ship detection within complex maritime environments using Oriented Boun…
A Visual Question Answering Method for SAR Ship: Breaking the Requirement for Multimodal Dataset Construction and Model Fine-Tuning
Fei Wang, Chengcheng Chen, Hongyu Chen +2
Current visual question answering (VQA) tasks often require constructing multimodal datasets and fine-tuning visual language models, which demands significant time and resources. T…
RSNet: A Light Framework for The Detection of SAR Ship Detection
Hongyu Chen, Chengcheng Chen, Fei Wang +2
Recent advancements in synthetic aperture radar (SAR) ship detection using deep learning have significantly improved accuracy and speed, yet effectively detecting small objects in…