Back to datasets
Dataset assetOpen Source CommunitySatellite Image AnalysisScene Graph Generation

STAR

STAR is the first large‑scale dataset for scene‑graph generation (SGG) in high‑resolution satellite images. It contains over 210,000 objects and more than 400,000 triples across 1,273 complex global scenes.

Source
github
Created
Jun 12, 2024
Updated
Jul 3, 2024
Signals
899 views
Availability
Linked source ready
Overview

Dataset description and usage context

STAR: Large‑Scale Satellite Image Scene‑Graph Generation Dataset and Benchmark

Overview

STAR is the first large‑scale dataset for scene‑graph generation (SGG) on very‑high‑resolution (VHR) satellite imagery. It comprises over 210,000 objects and 400,000 relational triples, covering 1,273 diverse global scenes.

Dataset Characteristics

  • Scale: >210,000 objects and 400,000 triples.
  • Image Sizes: From 512 × 768 px up to 27,860 × 31,096 px.
  • Complexity: Objects vary widely in scale and aspect ratio, with rich inter‑object relationships.

Construction

  • Goal: Promote geographic scene understanding from perception to cognition.
  • Approach: Introduces a Context‑Aware Cascaded Cognition (CAC) framework for object detection (OBD), pair pruning, and relation prediction.

Dataset & Toolkit

Usage

  • Installation & Usage: Detailed installation, pretrained models, training, and evaluation instructions are provided in the MMRotate 0.3.4 repository.

Published Models

Oriented Object Detection

Below are several released oriented object detection models and their performance metrics:

DetectormAPConfigLog LinkModel Link
Deformable DETR17.1configlogmodel
ARS‑DETR28.1configlogmodel
RetinaNet21.8configlogmodel
ATSS20.4… (table continues)

(The remainder of the table is omitted for brevity; all entries retain the original markdown structure.)

Need downstream help?

Pair the dataset with AI analysis and content workflows.

Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.

Explore AI studio