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.
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
- Links: STAR Dataset and 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:
| Detector | mAP | Config | Log Link | Model Link |
|---|---|---|---|---|
| Deformable DETR | 17.1 | config | log | model |
| ARS‑DETR | 28.1 | config | log | model |
| RetinaNet | 21.8 | config | log | model |
| ATSS | 20.4 | … (table continues) |
(The remainder of the table is omitted for brevity; all entries retain the original markdown structure.)
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.