dronefreak/lisa-rfdetr-nano

RF-DETR Nano Finetuned on LISA Traffic Lights

Fine-tuned RF-DETR Nano object detector on the LISA Traffic Lights 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.

---

Detection Showcase

---

Performance

Metric	Score (%)
mAP@50	27.47
mAP@50-95	12.16
Precision	N/A
Recall	N/A
F1 Score	N/A
Parameters	30.5M
FLOPs	N/A (not published upstream)

---

Evaluation Protocol

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

---

LISA Traffic Lights Model Zoo

Rank	Model	mAP@50	mAP@50-95	Precision	Recall
1	YOLOv26x	28.92	14.09	43.59	26.96
2	YOLOv26m	29.08	13.68	43.79	29.71
3	YOLOv26l	27.28	13.54	41.42	27.99
4	YOLOv11x	26.4	13.09	53.98	24.38
5	YOLOv26s	26.91	12.82	42.47	26.43
6	RF-DETR Nano	27.47	12.16	N/A	N/A
7	YOLOv8m	25.07	11.91	38.16	25.15
8	YOLOv26n	23.74	10.57	37.23	25.7

---

Per-Class Performance

Class	mAP@50	mAP@50-95
go	60.61	30.04
goForward	0.0	0.0
goLeft	14.61	4.53
stop	57.49	23.28
stopLeft	15.7	8.48
warning	43.13	18.57
warningLeft	0.73	0.24

---

Evaluation Visualizations

This model was evaluated with Supervision's MeanAveragePrecision, which reports mAP directly and does not produce PR-curve, F1-curve, or confusion-matrix plots. See the per-class table above for the full per-class breakdown; Precision/Recall/F1 are not available from this evaluation path and are reported as N/A.

---

Dataset

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

https://huggingface.co/datasets/dronefreak/LISA-Traffic-Lights

Classes

• go
• goForward
• goLeft
• stop
• stopLeft
• warning
• warningLeft

---

Usage

Install Dependencies

pip install rfdetr huggingface_hub

Load Model from Hugging Face

from huggingface_hub import hf_hub_download
import rfdetr

weights = hf_hub_download(
    repo_id="dronefreak/lisa-rfdetr-nano",
    filename="checkpoint_best_total.pth"
)

model = rfdetr.RFDETRNano(pretrain_weights=weights)

Run Inference

detections = model.predict("image.jpg", threshold=0.25)

---

Training Configuration

Setting	Value
Dataset	LISA Traffic Lights
Framework	RF-DETR
Training Toolkit	DetectionBench
Epochs (configured max)	500
Epochs (actually trained)	123
Early Stopping Patience	100
Batch Size	4
Resolution	384
Optimizer	adamw
Learning Rate	0.0001
Seed	42

---

Repository Contents

checkpoint_best_total.pth
metrics.csv
config.json
lisa_rfdetr-nano_showcase.jpg
README.md

---

Related Resources

• LISA Traffic Lights 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

• Rare/underrepresented arrow classes (goForward, goLeft, stopLeft, warningLeft) have far fewer training examples than the base go/stop/warning classes and correspondingly lower detection accuracy across every model in this zoo.
• Sequential dashcam video frames mean visually similar consecutive frames can appear within the same split; performance on genuinely novel scenes may differ from the reported test-split numbers.
• Trained and evaluated only on San Diego daytime/nighttime driving sequences (Pacific Beach, La Jolla); generalization to different traffic-light hardware, road layouts, or camera setups is untested.
• Small, distant traffic lights are harder to detect reliably, consistent with general small-object detection challenges.

---

Citation

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

1. The LISA Traffic Lights dataset (see below)
2. The original RF-DETR Nano architecture (see below)
3. DetectionBench, the training/evaluation framework used to produce this checkpoint

@article{jensen2016vision,
  title={Vision for looking at traffic lights: Issues, survey, and perspectives},
  author={Jensen, Morten Born{\o} and Philipsen, Mark Philip and M{\o}gelmose, Andreas and Moeslund, Thomas Baltzer and Trivedi, Mohan Manubhai},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  volume={17},
  number={7},
  pages={1800--1815},
  year={2016},
  doi={10.1109/TITS.2015.2509509},
  publisher={IEEE}
}

@inproceedings{philipsen2015traffic,
  title={Traffic light detection: A learning algorithm and evaluations on challenging dataset},
  author={Philipsen, Mark Philip and Jensen, Morten Born{\o} and M{\o}gelmose, Andreas and Moeslund, Thomas B and Trivedi, Mohan M},
  booktitle={Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on},
  pages={2341--2345},
  year={2015},
  organization={IEEE}
}

@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}
}

@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}
}