【ECCV2024】GeoText-1652 Benchmark

📰 News

• 2026-06-29: We launched the official GeoText-1652 Leaderboard for tracking community submissions on the full test set and the 24GB test split. Pull requests are welcome via leaderboard/data.json.
• We provide a GPU-friendly 24GB test split for CUDA out-of-memory cases. Download it from the Hugging Face dataset and use test_24G_version.json.

📚 About GeoText-1652

GeoText-1652 is a groundbreaking benchmark dataset for ECCV 2024, focusing on natural language-guided drone navigation with spatial relation matching. This dataset bridges the gap between natural language processing, computer vision, and robotics, paving the way for more intuitive and flexible drone control systems.

🌟 Key Features

• Multi-platform imagery: drone, satellite, and ground cameras
• Covers multiple universities with no overlap between train and test sets
• Rich annotations including global descriptions, bounding boxes, and spatial relations

📊 Dataset Statistics

Training and test sets all include the image, global description, bbox-text pair and building numbers. We note that there is no overlap between the 33 universities of the training set and the 39 universities of the test sets. Three platforms are considered, i.e., drone, satellite, and ground cameras.

Split	#Imgs	#Global Descriptions	#Bbox-Texts	#Classes	#Universities
Training (Drone)	37,854	113,562	113,367	701	33
Training (Satellite)	701	2,103	1,709	701	33
Training (Ground)	11,663	34,989	14,761	701	33
Test (Drone)	51,355	154,065	140,179	951	39
Test (Satellite)	951	2,853	2,006	951	39
Test (Ground)	2,921	8,763	4,023	793	39

🏆 Leaderboard

We maintain a community leaderboard for GeoText-1652. The primary ranking metric is r_mean, computed from Text R@1/R@5/R@10 and Image R@1/R@5/R@10. The tables below show a compact homepage view; see LEADERBOARD.md for all metrics, metadata, and submission details.

Primary Leaderboard: Full Test (951 buildings)

Rank	Method	Text R@1	Image R@1	Mean	Links
1	NGCG-MLLM (InternVL3.5-1B)	25.8	34.4	48.2	paper / code
2	SAA-DGL (X2-VLM)	16.7	29.4	39.7	paper
3	SAA-DGL (X-VLM)	14.9	28.2	38.8	paper
4	HCCM	14.7	28.8	38.2	paper / code
5	GeoText-1652 official checkpoint	13.6	26.3	36.1	paper / code

Hardware-friendly Split: 24GB Test

Rank	Method	Text R@1	Image R@1	Mean	Links
1	NGCG-MLLM (InternVL3.5-1B)	45.7	58.3	69.3	paper / code
2	SAA-DGL (X2-VLM)	31.9	53.3	61.4	paper
3	SAA-DGL (X-VLM)	30.7	52.1	60.7	paper
4	GeoText-1652 official checkpoint	29.9	50.1	58.7	paper / code

To submit a result, open a pull request that adds your entry to leaderboard/data.json. See LEADERBOARD.md for the full submission format.

💾 Download Links

• Google Drive: GeoText-1652 Dataset
• HuggingFace Hub:
  • Dataset: truemanv5666/GeoText1652_Dataset
  • Model: truemanv5666/GeoText1652_model

📁 Dataset Structure

This dataset is designed to support the development and testing of models in geographical location recognition, providing images from multiple views at numerous unique locations.

Directory Structure

GeoText_Dataset_Official/
├── test/
│ ├── gallery_no_train(250)/
│ │ ├── 0001/
│ │ │ ├── drone_view.jpg
│ │ │ ├── street_view.jpg
│ │ │ ├── satellite_view.jpg
│ │ ├── 0002/
│ │ ├── ... // More locations
│ │ ├── 0250/
│ ├── query(701)/
│ │ ├── 0001/
│ │ │ ├── drone_view.jpg
│ │ │ ├── street_view.jpg
│ │ │ ├── satellite_view.jpg
│ │ ├── 0002/
│ │ ├── ... // More locations
│ │ ├── 0701/
├── train/
│ ├── 0001/
│ │ ├── drone_view.jpg
│ │ ├── street_view.jpg
│ │ ├── satellite_view.jpg
│ ├── 0002/
│ ├── ... // More locations
│ ├── 0701/
├── test_951_version.json
├── train.json

Annotation Details

Example entry in train.json:

{
  "image_id": "0839/image-43.jpeg",
  "image": "train/0839/image-43.jpeg",
  "caption": "In the center of the image is a large, modern office building...",
  "sentences": [
    "The object in the center of the image is a large office building with several floors and a white facade",
    "On the upper middle side of the building, there is a street with cars driving on it",
    "On the middle right side of the building, there is a small parking lot with several cars parked in it"
  ],
  "bboxes": [
    [0.408688485622406, 0.6883664131164551, 0.38859522342681885, 0.6234817504882812],
    [0.2420489490032196, 0.3855597972869873, 0.30488067865371704, 0.2891976535320282],
    [0.7388443350791931, 0.8320053219795227, 0.5213109254837036, 0.33447015285491943]
  ]
}

• Caption: Provides a global description for the entire image.
• Sentences: Each sentence is aligned with a specific part of the image, related to the bounding boxes.
• Bounding Boxes: Specified as arrays of coordinates in the format [cx, cy, w, h].

🛠️ Setup and Usage Guide

Prerequisites

• Git
• Git Large File Storage (LFS)
• Conda

Installation Steps

1. Clone the repository:

   git clone https://github.com/MultimodalGeo/GeoText-1652.git
   

2. Install Miniconda:

   wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
   sh Miniconda3-latest-Linux-x86_64.sh
   

3. Create and activate conda environment:

   conda create -n gt python=3.8
   conda activate gt
   

4. Install requirements:

   cd GeoText-1652
   pip install -r requirements.txt
   

5. Install and configure Git LFS:

   apt install git-lfs
   git lfs install
   

6. Download dataset and model:

   git clone https://huggingface.co/datasets/truemanv5666/GeoText1652_Dataset
   git clone https://huggingface.co/truemanv5666/GeoText1652_model
   

7. Extract dataset images:

   cd GeoText1652_Dataset/images
   find . -type f -name "*.tar.gz" -print0 | xargs -0 -I {} bash -c 'tar -xzf "{}" -C "$(dirname "{}")" && rm "{}"'
   

8. Update configuration files:

   • Update re_bbox.yaml with correct paths
   • Update method/configs/config_swinB_384.json with correct ckpt path

Running the Model

From the Method directory:

cd Method

Evaluation

python3 run.py --task "re_bbox" --dist "l4" --evaluate --output_dir "output/eva" --checkpoint "/root/GeoText-1652/GeoText1652_model/geotext_official_checkpoint.pth"

Evaluation paths:

• Full test (951 cases): GeoText1652_Dataset/test_951_version.json
• 24GB GPU version (~190 cases): GeoText1652_Dataset/test_24G_version.json

24GB Version Results on Two 3090Ti:

| Text Query | Image Query |
|R@1  R@5  R@10|R@1  R@5  R@10|
|----|----|----|----|----|----| 
|29.9|46.3|54.1|50.1|81.2|90.3|

Full evaluation results are in the paper.

Leaderboard submissions should report the six metrics printed by Method/re_bbox.py: txt_r1, txt_r5, txt_r10, img_r1, img_r5, and img_r10.

Training

nohup python3 run.py --task "re_bbox" --dist "l4" --output_dir "output/train" --checkpoint "/root/GeoText-1652/GeoText1652_model/geotext_official_checkpoint.pth" &

🔗 Ecosystem

Explore our ecosystem for UAV & Spatial Intelligence 🚁

🚁 UAV & Spatial Intelligence

🎓 The University-1652 Family

🚀 New Open-Source Releases

---

⭐ If you find our projects helpful, a star is the best support! ⭐

📄 Citation

If you find GeoText-1652 useful for your work, please cite:

@inproceedings{chu2024towards, 
  title={Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching}, 
  author={Chu, Meng and Zheng, Zhedong and Ji, Wei and Wang, Tingyu and Chua, Tat-Seng}, 
  booktitle={ECCV}, 
  year={2024} 
}

🙏 Acknowledgements

We would like to express our gratitude to the creators of X-VLM for their excellent work, which has significantly contributed to this project.