dronefreak/exdark-yolov9m

YOLOv9m Finetuned on ExDark

Fine-tuned YOLOv9m object detector on the ExDark benchmark dataset, trained and evaluated as part of DetectionBench -- a framework for reproducibly benchmarking modern object detectors with identical training recipes and evaluation metrics across multiple real-world datasets.

<br>

<!-- ROW 1: Identity & Tech Stack --> <div style="display: flex; justify-content: center; align-items: center; gap: 8px; margin-bottom: 8px; flex-wrap: wrap;"> <img src="https://img.shields.io/badge/Task-ObjectDetection-blue?style=flat-square" alt="Task"> <img src="https://img.shields.io/badge/Framework-UltralyticsYOLO-0aa1a7?style=flat-square" alt="Framework"> <img src="https://img.shields.io/badge/Base_Model-YOLOv9m-purple?style=flat-square" alt="Base Model"> </div>

<!-- ROW 2: Performance Metrics --> <div style="display: flex; justify-content: center; align-items: center; gap: 8px; margin-bottom: 8px; flex-wrap: wrap;"> <img src="https://img.shields.io/badge/mAP@50-74.17%25-success?style=flat-square" alt="mAP@50"> <img src="https://img.shields.io/badge/mAP@50:95-47.38%25-orange?style=flat-square" alt="mAP@50:95"> <img src="https://img.shields.io/badge/Params-20.2M-lightgrey?style=flat-square" alt="Params"> </div>

<!-- ROW 3: Metadata --> <div style="display: flex; justify-content: center; align-items: center; gap: 8px; margin-bottom: 24px; flex-wrap: wrap;"> <img src="https://img.shields.io/badge/License-AGPL--3.0-lightgrey?style=flat-square" alt="License"> <a href="https://github.com/dronefreak/DetectionBench"><img src="https://img.shields.io/badge/Source-DetectionBench-black?style=flat-square" alt="Source"></a> </div>

Detection Showcase

<p align="center"> <img src="exdarkyolov9mshowcase.jpg" alt="ExDark Detection Demo" width="900"> </p>

Performance

Evaluation Protocol

Metrics reported in this model card are computed on the ExDark test split, using DetectionBench's standard evaluation pipeline (detectionbench-evaluate).

ExDark Model Zoo

Every model DetectionBench has trained and evaluated on ExDark so far, for full transparency -- see DetectionBench for the smaller, curated comparison set used on the project README.

Per-Class Performance

Evaluation Visualizations

Precision-Recall Curve

[image]

F1 Curve

[image]

Confusion Matrix

[image]

Dataset

This model was trained on ExDark. For the full dataset description, provenance, license, and citation, see the dataset card:

https://huggingface.co/datasets/dronefreak/ExDark

Classes

• —Bicycle
• —Boat
• —Bottle
• —Bus
• —Car
• —Cat
• —Chair
• —Cup
• —Dog
• —Motorbike
• —People
• —Table ---

Usage

Install Dependencies

pip install ultralytics huggingface_hub

Load Model from Hugging Face

from huggingface_hub import hf_hub_download
from ultralytics import YOLO

weights = hf_hub_download(
    repo_id="dronefreak/exdark-yolov9m",
    filename="best.pt"
)

model = YOLO(weights)

Run Inference

results = model.predict(
    source="image.jpg",
    conf=0.25
)

results[0].show()

Training Configuration

Repository Contents

best.pt
results.csv
args.yaml
BoxPR_curve.png
BoxF1_curve.png
confusion_matrix.png
val_batch0_pred.jpg
exdark_yolov9m_showcase.jpg
README.md

Related Resources

• —ExDark dataset card on Hugging Face
• —DetectionBench -- reproducible benchmarks for modern object detectors on real-world datasets

Training Framework

This model was trained using DetectionBench, an open-source framework for benchmarking object detectors across multiple real-world datasets with a common pipeline.

Features include:

• —A dataset-adapter registry for converting real-world datasets into a canonical format
• —Identical training/evaluation recipes across model families (Ultralytics YOLO/RT-DETR, RF-DETR)
• —Hardware profiling (latency, FPS, VRAM, parameters, FLOPs)
• —One-command reproducibility via versioned Hydra configs

If you find this model useful, please consider starring the repository.

Known Limitations

• —Severe class imbalance: People accounts for roughly 46% of all annotated boxes while Bus is the rarest class, so per-class accuracy on rare classes is measured on very few test examples and should be read with wide uncertainty.
• —Small dataset overall (7,344 images, 734 in the test split, across 12 classes) -- limited training signal for several classes independent of the imbalance above.
• —Two-hop provenance: this dataset was converted to YOLO format by a third-party Roboflow export before reaching DetectionBench, not sourced directly from the original per-class-folder release; images are pre-resized to 640x640 by that export.
• —The original authors separately request non-commercial use of this dataset (beyond the BSD-3-Clause license text itself) -- this applies to any model trained on it, not only the raw images. ---

Citation

If you use this model in your research, please consider citing:

1. 1.The ExDark dataset (see below)
2. 2.The original YOLOv9m architecture (see below)
3. 3.The other model architectures shown in the Model Zoo/External Comparison tables above, if you reference their results
4. 4.DetectionBench, the training/evaluation framework used to produce this checkpoint

@article{Exdark,
  title = {Getting to Know Low-light Images with The Exclusively Dark Dataset},
  author = {Loh, Yuen Peng and Chan, Chee Seng},
  journal = {Computer Vision and Image Understanding},
  volume = {178},
  pages = {30-42},
  year = {2019},
  doi = {https://doi.org/10.1016/j.cviu.2018.10.010}
}

@article{wang2024yolov9,
  title={YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information},
  author={Wang, Chien-Yao and Yeh, I-Hau and Liao, Hong-Yuan Mark},
  journal={arXiv preprint arXiv:2402.13616},
  year={2024}
}

Other architectures compared against on ExDark in this model card:

RF-DETR

@inproceedings{robinson2026rfdetr,
  title     = {RF-DETR: Real-Time Detection Transformer},
  author    = {Robinson, Isaac and Robicheaux, Peter and Popov, Matvei and Ramanan, Deva and Peri, Neehar},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2026},
  url       = {https://arxiv.org/abs/2511.09554}
}

@article{oquab2023dinov2,
  title={DINOv2: Learning Robust Visual Features without Supervision},
  author={Oquab, Maxime and Darcet, Timoth{\'e}e and Moutakanni, Theo and Vo, Huy and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and others},
  journal={arXiv preprint arXiv:2304.07193},
  year={2023}
}

YOLOv11

No official YOLO11 research paper has been published by Ultralytics; the most commonly cited independent architectural analysis is used instead:

@article{khanam2024yolov11,
  title={YOLOv11: An Overview of the Key Architectural Enhancements},
  author={Khanam, Rahima and Hussain, Muhammad},
  journal={arXiv preprint arXiv:2410.17725},
  year={2024}
}

YOLOv26

@article{jocher2026yolo26,
  title={Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models},
  author={Jocher, Glenn and Qiu, Jing and Liu, Mengyu and Lyu, Shuai and Akyon, Fatih Cagatay and Kalfaoglu, Muhammet Esat},
  journal={arXiv preprint arXiv:2606.03748},
  year={2026}
}

YOLOv8

No official YOLOv8 research paper has been published by Ultralytics; this is their own recommended software citation instead:

@software{jocher2023yolov8,
  author = {Glenn Jocher and Ayush Chaurasia and Jing Qiu},
  title = {Ultralytics YOLOv8},
  version = {8.0.0},
  year = {2023},
  url = {https://github.com/ultralytics/ultralytics},
  license = {AGPL-3.0}
}

@software{Saksena_DetectionBench_2026,
  author = {Saksena, Saumya Kumaar},
  title = {DetectionBench: Reproducible Benchmarks for Modern Object Detectors on Real-World Datasets},
  url = {https://github.com/dronefreak/DetectionBench},
  year = {2026}
}