YOLO26m Finetuned on SeaDronesSee

Fine-tuned YOLO26m object detector on the SeaDronesSee 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.

SeaDronesSee Detection Demo

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/seadronessee-yolo26m",
    filename="best.pt"
)

model = YOLO(weights)

Run Inference

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

results[0].show()

Performance

Evaluated on the SeaDronesSee val split, using DetectionBench's standard evaluation pipeline (detectionbench-evaluate).

Metric	Score (%)
mAP@50	82.38
mAP@50-95	49.57
Precision	90.01
Recall	81.18
F1 Score	85.37
Parameters	21.9M
FLOPs	75.4B (at 640 px)

SeaDronesSee Model Zoo

Every model DetectionBench has trained and evaluated on SeaDronesSee 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
RF-DETR Medium	83.47	47.49	87.01	83.33
YOLO26m	82.38	49.57	90.01	81.18
RF-DETR Small	80.97	45.31	85.68	80.16
YOLO26s	80.14	47.35	88.5	77.51
YOLO11x	74.82	45.56	87.37	72.46
YOLOv8s	72.94	43.05	84.52	71.25
RF-DETR Nano	72.38	39.83	81.37	74.08
YOLO11n	69.93	40.41	82.87	69.04
YOLOv8n	69.22	40.35	82.46	68.36
YOLOv8m	62.08	34.41	77.3	61.01

Per-Class Performance

Class	mAP@50	mAP@50-95
swimmer	81.35	34.4
boat	96.36	72.17
jetski	88.81	59.73
life_saving_appliances	62.05	29.17
buoy	83.32	52.4

Dataset

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

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

Classes

swimmer
boat
jetski
life_saving_appliances
buoy

Training Configuration

Setting	Value
Dataset	SeaDronesSee
Framework	Ultralytics YOLO
Training Toolkit	DetectionBench
Epochs (configured max)	500
Epochs (actually trained)	157
Early Stopping Patience	100
Batch Size	32
Image Size	640
Optimizer	auto
Initial Learning Rate	0.001
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
seadronessee_yolo26m_showcase.jpg
README.md

Related Resources

SeaDronesSee 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: swimmer (64.22%) and boat (22.55%) account for roughly 87% of all annotated boxes in the training set, while life_saving_appliances (1.60%) is rare -- per-class accuracy on the minority classes is measured on comparatively few examples.
Small-object heavy: objects are captured from altitude over open water, so roughly 79% of boxes cover under 0.1% of the image area -- swimmers and buoys in particular are small, low-contrast targets against water.
No public test-split labels: the official images/test/ split is a held-out competition set with no released ground truth, so these models are evaluated on the valid split instead of test -- the number reported here is not directly comparable to official SeaDronesSee leaderboard submissions, which score against the held-out test set via the benchmark's own server.
A maritime search-and-rescue benchmark specifically: generalization to non-maritime aerial scenes, different water/lighting conditions, or altitudes outside this dataset's capture range is untested.

Citation

If you use this model in your research, please consider citing the dataset and the model architecture:

@inproceedings{varga2022seadronessee,
  title={SeaDronesSee: A maritime benchmark for detecting humans in open water},
  author={Varga, Leon Amadeus and Kiefer, Benjamin and Messmer, Martin and Zell, Andreas},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages={2260--2270},
  year={2022}
}

@misc{varga2021seadronesseemaritimebenchmarkdetecting,
      title={SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water},
      author={Leon Amadeus Varga and Benjamin Kiefer and Martin Messmer and Andreas Zell},
      year={2021},
      eprint={2105.01922},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2105.01922}
}

@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}
}