dronefreak/visdrone-yolov8s

YOLOv8s Finetuned on VisDrone-DET

Fine-tuned YOLOv8s object detector on the VisDrone-DET 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.

---

Performance

Metric	Score (%)
mAP@50	43.47
mAP@50-95	25.77
Precision	56.09
Recall	44.51
F1 Score	49.63
Parameters	11.2M
FLOPs	28.6B (at 640 px)

---

Evaluation Protocol

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

---

VisDrone-DET Model Zoo

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

Model	mAP@50	mAP@50-95	Precision	Recall
YOLOv9s	45.38	26.95	56.95	46.19
YOLOv10s	44.51	26.28	55.97	45.61
YOLOv8s	43.47	25.77	56.09	44.51
YOLOv9t	40.67	23.73	52.84	41.78
YOLOv26n	39.9	22.95	51.14	42.08
YOLOv10n	39.8	23.08	51.22	41.5
YOLOv8n	39.69	23.03	52.02	41.36
YOLOv11n	39.52	23.0	51.49	41.02
RF-DETR Nano	37.92	20.88	69.02	46.21

---

Earlier VisDrone-DET Results (Companion Codebase)

The rows below are earlier VisDrone2019-DET runs (test split) from a separate companion codebase (VisDrone-dataset-python-toolkit), not reproduced inside DetectionBench and kept here for context and history. Where a model also appears in the Model Zoo table above, that row is the current DetectionBench run and supersedes the one here -- for example the earlier YOLOv9t run used 640 px inputs and 300 epochs, while the current DetectionBench YOLO runs use 1280 px. The RF-DETR rows are earlier DetectionBench-trained runs at RF-DETR's default input sizes (384/512/576 px).

Model	mAP@50	mAP@50-95	Precision	Recall
YOLOv9e	40.02	23.73	54.78	42.42
YOLOv11x	38.44	22.6	52.41	41.43
YOLOv26x	38.33	22.48	52.91	41.06
YOLOv11l	37.14	21.85	51.87	40.33
YOLOv10x	37.24	21.81	52.59	39.84
YOLOv26l	37.65	21.75	51.6	40.42
YOLOv9c	37.22	21.73	51.99	39.77
YOLOv8x	36.81	21.52	51.91	39.78
YOLOv26m	36.67	21.22	51.03	39.79
YOLOv10l	35.95	21.09	52.13	38.48
YOLOv11m	36.35	21.02	50.24	39.46
YOLOv9m	36.19	20.95	51.05	39.12
RF-DETR-Medium	36.82	20.14	64.0	47.05
YOLOv8m	34.39	19.95	48.18	38.2
YOLOv9s	33.52	19.26	46.16	37.43
YOLOv11s	32.3	18.47	45.49	35.31
YOLOv8s	31.95	18.24	45.99	35.49
YOLOv26s	32.1	18.06	45.75	35.05
RF-DETR-Small	33.25	17.88	62.62	43.51
YOLOv9t	29.09	16.22	42.57	32.66
YOLOv8n	28.18	15.77	40.86	31.81
YOLOv11n	27.59	15.46	39.58	31.74
YOLOv10n	27.65	15.32	41.02	31.68
YOLOv26n	26.73	14.64	38.6	31.14
RF-DETR-Nano	25.15	12.77	58.99	35.0
rt_detr_l	21.68	9.34	35.76	26.3
Source: https://huggingface.co/collections/dronefreak/visdrone-object-detection-model-zoo

---

Per-Class Performance

Class	mAP@50	mAP@50-95
pedestrian	43.83	18.75
people	27.18	10.09
bicycle	22.34	10.13
car	81.99	53.56
van	47.71	33.21
truck	50.0	33.68
tricycle	30.14	17.7
awning-tricycle	23.52	14.78
bus	62.63	45.78
motor	45.32	20.06
others	0.0	0.0

---

Evaluation Visualizations

Precision-Recall Curve

F1 Curve

Confusion Matrix

Normalized Confusion Matrix

---

Dataset

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

https://huggingface.co/datasets/Voxel51/VisDrone2019-DET

Classes

• pedestrian
• people
• bicycle
• car
• van
• truck
• tricycle
• awning-tricycle
• bus
• motor
• others

---

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/visdrone-yolov8s",
    filename="best.pt"
)

model = YOLO(weights)

Run Inference

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

results[0].show()

---

Training Configuration

Setting	Value
Dataset	VisDrone-DET
Framework	Ultralytics YOLO
Training Toolkit	DetectionBench
Epochs (configured max)	100
Epochs (actually trained)	100
Early Stopping Patience	25
Batch Size	auto (Ultralytics AutoBatch)
Image Size	1280
Optimizer	SGD
Initial Learning Rate	0.01
Seed	0

---

Repository Contents

best.pt
results.csv
args.yaml
BoxPR_curve.png
BoxF1_curve.png
BoxP_curve.png
BoxR_curve.png
confusion_matrix.png
confusion_matrix_normalized.png
val_batch0_pred.jpg
visdrone_yolov8s_showcase.jpg
assets/demo_banner.mp4
assets/demo_banner_poster.jpg
README.md

---

Related Resources

• VisDrone-DET 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: car (42.21%) and pedestrian (23.12%) account for two-thirds of all annotated boxes in the training set, while awning-tricycle (0.95%) and tricycle (1.40%) are rare -- the others class has zero annotated instances in the training set entirely and is effectively unusable (always 0 AP).
• Extreme small-object density: ~53 annotated boxes per image on average, with roughly 69% of boxes covering under 0.1% of the image area -- consistent with VisDrone's aerial small-object detection challenge (objects captured from significant altitude).
• The original authors license VisDrone under CC BY-NC-SA 3.0 -- non-commercial research use only (see the dataset's homepage); this applies to any model trained on it, not only the raw images.
• These RF-DETR checkpoints were trained/evaluated directly through DetectionBench. The YOLO/RT-DETR rows in the External VisDrone Model Zoo comparison below were trained via a separate companion codebase, not reproduced inside DetectionBench -- see that collection for their own training details and caveats.

---

Citation

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

1. The VisDrone-DET dataset (see below)
2. The original YOLOv8s architecture (see below)
3. The other model architectures shown in the Model Zoo/External Comparison tables above, if you reference their results
4. DetectionBench, the training/evaluation framework used to produce this checkpoint

@article{zhu2018vision,
  title={Vision meets drones: A challenge},
  author={Zhu, Pengfei and Wen, Longyin and Bian, Xiao and Ling, Haibin and Hu, Qinghua},
  journal={arXiv preprint arXiv:1804.07437},
  year={2018}
}

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}
}

Other architectures compared against on VisDrone-DET 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}
}

YOLOv10

@article{wang2024yolov10,
  title={YOLOv10: Real-Time End-to-End Object Detection},
  author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
  journal={arXiv preprint arXiv:2405.14458},
  year={2024}
}

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}
}

YOLOv9

@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}
}

@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}
}