KOMPSAT-3/3A Image-text Dataset for Training Large Multimodal Models

KOMPSAT-3/3A Image-text Dataset for Training Large Multimodal Models

This study aims to improve the accuracy and interpretability of large multimodal models (LMMs) specialized in satellite image analysis by constructing an image-text dataset based on KOMPSAT-3/3A imagery and presenting the results of training using this dataset. Conventional LMMs are primarily traine...

Full description

Saved in:
Bibliographic Details
Main Authors: Han Oh, Dong-Bin Shin, Dae-Won Chung
Format: Article
Language:English
Published: GeoAI Data Society 2025-03-01
Series:Geo Data
Subjects:
large multimodal model
satellite imagery
kompsat
image-text dataset
finetuning
Online Access:http://geodata.kr/upload/pdf/GD-2025-0003.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items