Skip to content

RF-DETR: Real-Time SOTA Detection and Segmentation Model

RF-DETR is a real-time transformer architecture for object detection and instance segmentation developed by Roboflow. Built on a DINOv2 vision transformer backbone, RF-DETR achieves state-of-the-art accuracy–latency trade-offs: RF-DETR-L reaches 56.5 AP50:95 on COCO at 6.8 ms (NVIDIA T4, TensorRT FP16), and RF-DETR-2XL achieves 60.1 AP50:95 — the first real-time model to exceed 60 AP on COCO. Accepted at ICLR 2026.

RF-DETR uses a DINOv2 vision transformer backbone and supports both detection and instance segmentation in a single, consistent API. Core models (Nano through Large) and all code are released under the Apache 2.0 license; XL and 2XLarge detection models require rfdetr[plus] and are provided under PML 1.0.

Developed by Isaac Robinson, Peter Robicheaux, Fedor Popov, Deva Ramanan (CMU), and Neehar Peri (CMU) at Roboflow. If you use RF-DETR in your research, please cite:

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

Install

You can install and use rfdetr in a Python>=3.10 environment. For detailed installation instructions, including installing from source, and setting up a local development environment, check out our install page.

Installation

version python-version license downloads

pip install rfdetr

uv pip install rfdetr

For uv projects:

uv add rfdetr

Quickstart

  • Run Detection Models

    Load and run pre-trained RF-DETR detection models.

    Tutorial

  • Run Segmentation Models

    Load and run pre-trained RF-DETR-Seg segmentation models.

    Tutorial

  • Train Models

    Learn how to fine-tune RF-DETR models for detection and segmentation.

    Tutorial

Tutorials

  • Train RF-DETR on a Custom Dataset. Video

    Train RF-DETR on a Custom Dataset

    End to end walkthrough of training RF-DETR on a custom dataset.

    Watch the video

  • Deploy RF-DETR to NVIDIA Jetson. Article

    Deploy RF-DETR to NVIDIA Jetson

    Instructions for deploying RF-DETR on NVIDIA Jetson with Roboflow Inference.

    Read the tutorial

  • Train and Deploy RF-DETR with Roboflow

    Train and Deploy RF-DETR with Roboflow

    Cloud training and hardware deployment workflow using Roboflow.

    Read the tutorial

Benchmarks

RF-DETR achieves the best accuracy–latency trade-off among real-time object detection and instance segmentation models — both on COCO and on the more demanding RF100-VL benchmark (domain adaptability). For detailed benchmark tables and methodology, check out our benchmarks page.

Detection

Pareto front — detection accuracy vs latency: RF-DETR-2XL achieves 78.5 COCO AP50 (60.1 AP50:95) at 17.2 ms; RF-DETR-L achieves 75.1 AP50 at 6.8 ms, outperforming YOLO11x at comparable latency

Architecture COCO AP50 COCO AP50:95 RF100VL AP50 RF100VL AP50:95 Latency (ms) Params (M) Resolution
RF-DETR-N 67.6 48.4 85.0 57.7 2.3 30.5 384×384
RF-DETR-S 72.1 53.0 86.7 60.2 3.5 32.1 512×512
RF-DETR-M 73.6 54.7 87.4 61.2 4.4 33.7 576×576
RF-DETR-L 75.1 56.5 88.2 62.2 6.8 33.9 704×704
RF-DETR-XL 77.4 58.6 88.5 62.9 11.5 126.4 700×700
RF-DETR-2XL 78.5 60.1 89.0 63.2 17.2 126.9 880×880

Segmentation

Pareto front — segmentation accuracy vs latency: RF-DETR-Seg-2XL achieves 73.1 COCO AP50 (49.9 AP50:95) at 21.8 ms; RF-DETR-Seg-L achieves 70.5 AP50 at 8.8 ms

Architecture COCO AP50 COCO AP50:95 Latency (ms) Params (M) Resolution
RF-DETR-Seg-N 63.0 40.3 3.4 33.6 312×312
RF-DETR-Seg-S 66.2 43.1 4.4 33.7 384×384
RF-DETR-Seg-M 68.4 45.3 5.9 35.7 432×432
RF-DETR-Seg-L 70.5 47.1 8.8 36.2 504×504
RF-DETR-Seg-XL 72.2 48.8 13.5 38.1 624×624
RF-DETR-Seg-2XL 73.1 49.9 21.8 38.6 768×768

Frequently Asked Questions

What is RF-DETR? RF-DETR (Roboflow Detection Transformer) is a real-time object detection and instance segmentation model from Roboflow, accepted at ICLR 2026. It uses a DINOv2 vision transformer backbone and achieves state-of-the-art accuracy–latency trade-offs on COCO (60.1 AP50:95 for RF-DETR-2XL) and RF100-VL.

How does RF-DETR compare to YOLOv11? RF-DETR-L achieves 56.5 AP50:95 on COCO at 6.8 ms latency on an NVIDIA T4, outperforming YOLOv11x (54.7 AP) at lower latency. The DINOv2 backbone gives RF-DETR stronger performance on domain-shift benchmarks such as RF100-VL.

What GPU is required to train RF-DETR? A CUDA-capable GPU with at least 8 GB VRAM (e.g., NVIDIA RTX 3060, T4, A10) is recommended for fine-tuning. Smaller models (RF-DETR-N and RF-DETR-S) can fit in 6 GB VRAM with reduced batch size. CPU inference is supported for evaluation.

Which dataset formats does RF-DETR support? RF-DETR supports COCO JSON and YOLO-format datasets (with dataset_file: "yolo"). Roboflow datasets export directly to both formats. Detection and segmentation datasets use the same format — the model variant determines the task.

Can RF-DETR run in real time? Yes. RF-DETR-N runs at 2.3 ms per frame on a T4 GPU (TensorRT FP16, batch 1), and RF-DETR-L at 6.8 ms — both well within real-time thresholds. ONNX and TFLite exports are available for edge deployment.

What is the difference between RF-DETR detection and segmentation models? Detection models (e.g., RFDETRLarge) output bounding boxes. Segmentation models (e.g., RFDETRSegLarge) additionally output instance masks. Both share the same backbone and training API; segmentation adds a mask head and requires COCO-format segmentation annotations.

Is RF-DETR open source? Yes. Core models (Nano through Large) and all training/inference code are released under the Apache 2.0 license. XLarge and 2XLarge models require the rfdetr[plus] package (PML 1.0 license).

How do I fine-tune RF-DETR on a custom dataset? Instantiate a model and call model.train(...) with your dataset directory in COCO JSON or YOLO format. Example: model = RFDETRLarge(); model.train(dataset_dir='./dataset', epochs=50, batch_size=4). The model downloads pretrained weights automatically and resumes from the best checkpoint.

How do I export RF-DETR to ONNX or TensorRT? Call model.export(format="onnx") after training or loading a checkpoint. ONNX export works on CPU and produces a single .onnx file compatible with ONNX Runtime and OpenCV DNN. For TensorRT deployment, first export to ONNX and then convert the .onnx model with TensorRT tooling or helpers such as trtexec; this requires TensorRT and a CUDA GPU.

Which RF-DETR model size should I use? RF-DETR-Nano (2.3 ms, 67.6 AP50 on COCO) is best for edge and real-time applications. RF-DETR-Large (6.8 ms, 56.5 AP50:95) offers the best accuracy–latency trade-off for server deployment. RF-DETR-2XLarge (17.2 ms, 60.1 AP50:95) maximizes accuracy when latency allows.