RF-DETR: Real-Time SOTA Object Detection, Instance Segmentation, and Keypoint Detection

---

RF-DETR is a real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow. Built on a DINOv2 vision transformer backbone (a PE-Core-T backbone for Atto, Femto and Pico), RF-DETR delivers state-of-the-art accuracy and latency trade-offs on Microsoft COCO and RF100-VL.

RF-DETR supports object detection, instance segmentation, and keypoint detection (preview) in a single, consistent API.

Commercially usable under Apache 2.0. The rfdetr package, RF-DETR Nano, Small, Medium and Large detection, every RF-DETR-Seg size (Nano through 2XLarge), and RF-DETR Keypoint are released under the Apache 2.0 license, so they're commercially usable out of the box: you can ship them in closed-source, commercial products, including self-hosted deployments, without paying a license fee or open-sourcing your code. RF-DETR Atto, Femto, Pico, XL and 2XL detection ship in the optional rfdetr[plus] extension under the Roboflow Platform Model License (PML 1.0): commercial use is included when you deploy on Roboflow, and commercial self-hosting requires the Enterprise add-on. See License.

The published RF-DETR sizes were created with neural architecture search (NAS) — and the same NAS method is now available on the Roboflow platform, so you can discover the best architecture for your own dataset. Learn more in the NAS docs.

https://github.com/user-attachments/assets/add23fd1-266f-4538-8809-d7dd5767e8e6

Install

To install RF-DETR, install the rfdetr package in a Python>=3.10 environment with pip.

pip install rfdetr

pip install rfdetr gives you only Apache 2.0 RF-DETR code and models, so it's commercially usable out of the box. pip install "rfdetr[plus]" adds the Atto, Femto, Pico, XL and 2XL detection models under PML 1.0 (commercial use included on Roboflow; commercial self-hosting requires the Enterprise add-on). See License.

By installing RF-DETR from source, you can explore the most recent features and enhancements that have not yet been officially released. Please note that these updates are still in development and may not be as stable as the latest published release.

pip install https://github.com/roboflow/rf-detr/archive/refs/heads/develop.zip

Benchmarks

RF-DETR achieves state-of-the-art results in both object detection and instance segmentation, with benchmarks reported on Microsoft COCO and RF100-VL (RF100-VL for detection only). The charts and tables below compare RF-DETR against other top real-time models across accuracy and latency for detection and segmentation. All COCO accuracy numbers are measured in-house for every model shown, computed with pycocotools in SAB over the full 5,000-image val2017 split, so every row is directly comparable and may differ from vendor-reported figures. The sole exception is rows marked †, which are quoted from the original authors' paper and were not measured in SAB. All latency numbers were measured on an NVIDIA T4 using TensorRT, FP16, and batch size 1. Parameter counts are deployment (fused) nn.Module parameter counts (model.parameters(), not the raw tensor count of the saved checkpoint), except rows marked †, which are the authors' reported counts. For full benchmarking methodology and reproducibility details, see roboflow/sab.

License note: YOLOv8, YOLO11 and YOLO26 are released under AGPL-3.0. In practice, using them in a commercial product or service, including one users reach over a network, means open-sourcing your application code under AGPL-3.0 or buying a commercial license. Deploying on Roboflow includes a commercial license for these models for every user; commercial self-hosting is an Enterprise add-on (details). RF-DETR rows marked Apache 2.0 are commercially usable out of the box; rows marked PML 1.0 include commercial use on Roboflow, and commercial self-hosting requires the Enterprise add-on. LW-DETR and D-FINE are Apache 2.0.

Detection

Architecture	COCO AP50	COCO AP50:95	RF100VL AP50	RF100VL AP50:95	Latency (ms)	Params (M)	Resolution	License
RF-DETR-A △	49.4	30.5	78.2	48.3	1.0	7.4	380x380	PML 1.0
RF-DETR-F △	55.9	37.8	82.5	53.8	1.4	7.9	384x384	PML 1.0
RF-DETR-P △	60.2	41.6	84.1	56.0	1.7	8.4	560x560	PML 1.0
RF-DETR-N	67.6	48.4	85.0	57.7	2.3	30.5	384x384	Apache 2.0
RF-DETR-S	72.1	53.0	86.7	60.2	3.5	32.1	512x512	Apache 2.0
RF-DETR-M	73.6	54.7	87.4	61.2	4.4	33.7	576x576	Apache 2.0
RF-DETR-L	75.1	56.5

† Reported by the SAM 3 authors (arXiv:2511.16719, Table 36), not measured by us in SAB. The value is SAM 3 fine-tuned on the full RF100-VL training set, which is the same setting as the RF100VL columns above — SAM 3's paper reports LW-DETR-m at 59.8 on this benchmark, matching our own measurement, so the numbers line up. Dashes mark results SAM 3 does not report under this protocol. Parameter count is the paper's stated ~850 M (~450 M vision + ~300 M text encoders + ~100 M detector/tracker).

Segmentation

Architecture	COCO AP50	COCO AP50:95	Latency (ms)	Params (M)	Resolution	License
RF-DETR-Seg-N	63.0	40.3	3.4	33.6	312x312	Apache 2.0
RF-DETR-Seg-S	66.2	43.1	4.4	33.7	384x384	Apache 2.0
RF-DETR-Seg-M	68.4	45.3	5.9	35.7	432x432	Apache 2.0
RF-DETR-Seg-L	70.5	47.1	8.8	36.2	504x504	Apache 2.0
RF-DETR-Seg-XL	72.2	48.8	13.5	38.1	624x624	Apache 2.0
RF-DETR-Seg-2XL	73.1	49.9	21.8	38.6	768x768	Apache 2.0
YOLOv8-N-Seg	45.6	28.3	3.5	3.4	640x640	AGPL-3.0
YOLOv8-S-Seg	53.8	34.0	4.2	11.8	640x640	AGPL-3.0
YOLOv8-M-Seg

Keypoints

Architecture	COCO AP50:95	Latency (ms)	Params (M)	License
RF-DETR Keypoint (Preview)	71.8	9.7	40.7	Apache 2.0
YOLO11-pose N	48.9	3.2	2.9	AGPL-3.0
YOLO11-pose S	57.5	3.4	9.9	AGPL-3.0
YOLO11-pose M	64.2	5.2	20.9	AGPL-3.0
YOLO11-pose L	65.2	6.6	26.2	AGPL-3.0
YOLO11-pose X	68.6	10.6	58.8	AGPL-3.0
YOLO26-pose N	55.9	1.9	2.9	AGPL-3.0
YOLO26-pose S	62.0	2.7	10.4	AGPL-3.0
YOLO26-pose M	68.0	4.6	21.5	AGPL-3.0
YOLO26-pose L	69.2	5.9	25.9	AGPL-3.0
YOLO26-pose X	71.0	9.8	57.6	AGPL-3.0

Keypoint benchmarks report AP50:95 (OKS-based); this is the standard COCO keypoint comparison metric.

NAS on the Roboflow Platform

Since the paper release, we have improved RF-DETR NAS training on the Roboflow platform even further. A single training run gives you every model size, with results that beat not only the open-source checkpoints but also our own paper NAS results. Try it now!

Run Models

Detection

RF-DETR provides multiple model sizes, ranging from Nano to 2XLarge. To use a different model size, replace the class name in the code snippet below with another class from the table.

import supervision as sv
from rfdetr import RFDETRMedium
from rfdetr.assets.coco_classes import COCO_CLASSES

model = RFDETRMedium()

detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5)

labels = [f"{COCO_CLASSES[class_id]}" for class_id in detections.class_id]

annotated_image = sv.BoxAnnotator().annotate(detections.metadata["source_image"], detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels)

Note: COCO_CLASSES works for COCO-pretrained models. For fine-tuned models, use detections.data["class_name"] instead — it resolves class names from the checkpoint and works for both COCO and custom datasets.

You can also run RF-DETR models using the Inference library. To switch model size, select the appropriate inference package alias from the table below.

import requests
import supervision as sv
from PIL import Image
from inference import get_model

model = get_model("rfdetr-medium")

image = Image.open(requests.get("https://media.roboflow.com/dog.jpg", stream=True).raw)
predictions = model.infer(image, confidence=0.5)[0]
detections = sv.Detections.from_inference(predictions)

annotated_image = sv.BoxAnnotator().annotate(image, detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections)

Size	RF-DETR package class	Inference package alias	COCO AP50	COCO AP50:95	Latency (ms)	Params (M)	Resolution	License
A	RFDETRAtto △	rfdetr-atto	49.4	30.5	1.0	7.4	380x380	PML 1.0
F	RFDETRFemto △	rfdetr-femto	55.9	37.8	1.4	7.9	384x384	PML 1.0
P	RFDETRPico △	rfdetr-pico	60.2	41.6	1.7	8.4	560x560	PML 1.0
N	RFDETRNano	rfdetr-nano	67.6	48.4	2.3	30.5	384x384	Apache 2.0
S	RFDETRSmall	rfdetr-small	72.1	53.0	3.5	32.1	512x512	Apache 2.0
M	RFDETRMedium	rfdetr-medium	73.6	54.7	4.4

△ Requires the rfdetr_plus extension: pip install rfdetr[plus]. See License for details.

Segmentation

RF-DETR supports instance segmentation with model sizes from Nano to 2XLarge. To use a different model size, replace the class name in the code snippet below with another class from the table.

import supervision as sv
from rfdetr import RFDETRSegMedium
from rfdetr.assets.coco_classes import COCO_CLASSES

model = RFDETRSegMedium()

detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5)

labels = [f"{COCO_CLASSES[class_id]}" for class_id in detections.class_id]

annotated_image = sv.MaskAnnotator().annotate(detections.metadata["source_image"], detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels)

You can also run RF-DETR-Seg models using the Inference library. To switch model size, select the appropriate inference package alias from the table below.

import requests
import supervision as sv
from PIL import Image
from inference import get_model

model = get_model("rfdetr-seg-medium")

image = Image.open(requests.get("https://media.roboflow.com/dog.jpg", stream=True).raw)
predictions = model.infer(image, confidence=0.5)[0]
detections = sv.Detections.from_inference(predictions)

annotated_image = sv.MaskAnnotator().annotate(image, detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections)

Size	RF-DETR package class	Inference package alias	COCO AP50	COCO AP50:95	Latency (ms)	Params (M)	Resolution	License
N	RFDETRSegNano	rfdetr-seg-nano	63.0	40.3	3.4	33.6	312x312	Apache 2.0
S	RFDETRSegSmall	rfdetr-seg-small	66.2	43.1	4.4	33.7	384x384	Apache 2.0
M	RFDETRSegMedium	rfdetr-seg-medium	68.4	45.3	5.9	35.7	432x432	Apache 2.0
L	RFDETRSegLarge	rfdetr-seg-large	70.5	47.1	8.8	36.2	504x504	Apache 2.0
XL	RFDETRSegXLarge	rfdetr-seg-xlarge	72.2	48.8	13.5	38.1	624x624	Apache 2.0
2XL	RFDETRSeg2XLarge	rfdetr-seg-2xlarge	73.1	49.9

Keypoints

RF-DETR supports keypoint detection (preview) with RFDETRKeypointPreview, pretrained on COCO person keypoints.

from rfdetr import RFDETRKeypointPreview

model = RFDETRKeypointPreview()
key_points = model.predict("image.jpg", threshold=0.5)

Size	RF-DETR package class	COCO AP50:95	Latency (ms)	Params (M)	Resolution	License
Keypoint (Preview)	RFDETRKeypointPreview	71.8	9.7	40.7	576x576	Apache 2.0

Train Models

RF-DETR supports training for object detection, instance segmentation, and keypoint detection (preview). You can train models in Google Colab or directly on the Roboflow platform. Below you will find a step-by-step video fine-tuning tutorial.

Documentation

Visit our documentation website to learn more about how to use RF-DETR.

License

RF-DETR is commercially usable. Licensing is split by component:

Component	License	What it means in practice
rfdetr package (training, inference and export code)	Apache 2.0	Commercially usable out of the box: you can ship it in closed-source, commercial products, including self-hosted deployments, without paying a license fee or open-sourcing your code.
RF-DETR Nano, Small, Medium and Large detection	Apache 2.0	Same as above.
RF-DETR-Seg, every size (Nano through 2XLarge)	Apache 2.0	Same as above.
RF-DETR Keypoint (Preview)	Apache 2.0	Same as above.
RF-DETR Atto, Femto, Pico, XL and 2XL detection (rfdetr[plus]), and RF-DETR NAS models	Roboflow Platform Model License (PML 1.0)	Commercial use is included when you deploy on Roboflow; commercial self-hosting requires the Enterprise add-on (details).

Acknowledgements

Our work is built upon LW-DETR, DINOv2, and Deformable DETR. Thanks to their authors for their excellent work!

Citation

If you find our work helpful for your research, please consider citing the following BibTeX entry.

@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}
}

Contribute

We welcome and appreciate all contributions! If you notice any issues or bugs, have questions, or would like to suggest new features, please open an issue or pull request. By sharing your ideas and improvements, you help make RF-DETR better for everyone.

Project Activity

PyPI downloads cover completed Monday-to-Sunday periods and exclude known mirrors. New stars are calculated from consecutive scheduled GitHub snapshots.