FSAR-Cap: A Fine-Grained Two-Stage Annotated Dataset for SAR Image Captioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jinqi, Zhang, Lamei, Zou, Bin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908600723570688
author Zhang, Jinqi
Zhang, Lamei
Zou, Bin
author_facet Zhang, Jinqi
Zhang, Lamei
Zou, Bin
contents Synthetic Aperture Radar (SAR) image captioning enables scene-level semantic understanding and plays a crucial role in applications such as military intelligence and urban planning, but its development is limited by the scarcity of high-quality datasets. To address this, we present FSAR-Cap, a large-scale SAR captioning dataset with 14,480 images and 72,400 image-text pairs. FSAR-Cap is built on the FAIR-CSAR detection dataset and constructed through a two-stage annotation strategy that combines hierarchical template-based representation, manual verification and supplementation, prompt standardization. Compared with existing resources, FSAR-Cap provides richer fine-grained annotations, broader category coverage, and higher annotation quality. Benchmarking with multiple encoder-decoder architectures verifies its effectiveness, establishing a foundation for future research in SAR captioning and intelligent image interpretation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16394
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FSAR-Cap: A Fine-Grained Two-Stage Annotated Dataset for SAR Image Captioning
Zhang, Jinqi
Zhang, Lamei
Zou, Bin
Image and Video Processing
Synthetic Aperture Radar (SAR) image captioning enables scene-level semantic understanding and plays a crucial role in applications such as military intelligence and urban planning, but its development is limited by the scarcity of high-quality datasets. To address this, we present FSAR-Cap, a large-scale SAR captioning dataset with 14,480 images and 72,400 image-text pairs. FSAR-Cap is built on the FAIR-CSAR detection dataset and constructed through a two-stage annotation strategy that combines hierarchical template-based representation, manual verification and supplementation, prompt standardization. Compared with existing resources, FSAR-Cap provides richer fine-grained annotations, broader category coverage, and higher annotation quality. Benchmarking with multiple encoder-decoder architectures verifies its effectiveness, establishing a foundation for future research in SAR captioning and intelligent image interpretation.
title FSAR-Cap: A Fine-Grained Two-Stage Annotated Dataset for SAR Image Captioning
topic Image and Video Processing
url https://arxiv.org/abs/2510.16394