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

Introduction

RF-DETR is a real-time, transformer-based object detection and instance segmentation model architecture developed by Roboflow and released under the Apache 2.0 license.

RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO object detection benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models.

On image segmentation, RF-DETR Seg (Preview) is 3x faster and more accurate than the largest YOLO when evaluated on the Microsoft COCO Segmentation benchmark, defining a new real-time state-of-the-art for the industry-standard benchmark in segmentation model evaluation.

RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance.

Benchmark Results

Object Detection

We validated the performance of RF-DETR on both Microsoft COCO and the RF100-VL benchmarks.

See our full benchmarks.

Instance Segmentation

We benchmarked RF-DETR on the Microsoft COCO dataset for segmentation. Our results are below.

💻 Install

You can install and use rfdetr in a Python>=3.9 environment.

Installation

pip (recommended)poetryuvrye

pip install rfdetr

poetry add rfdetr

uv pip install rfdetr

For uv projects:

uv add rfdetr

rye add rfdetr

git clone (for development)

virtualenvuv

# clone repository and navigate to root directory
git clone --depth 1 -b develop https://github.com/roboflow/rf-detr.git
cd rf-detr

# setup python environment and activate it
python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip

# installation
pip install -e "."

# clone repository and navigate to root directory
git clone --depth 1 -b develop https://github.com/roboflow/rf-detr.git
cd rf-detr

# setup python environment and activate it
uv venv
source .venv/bin/activate

# installation
uv pip install -r pyproject.toml -e . --all-extras

🚀 Quickstart

• Run a Pre-Trained Model

  ---

  Load and run a pre-trained RF-DETR model.

  Tutorial

• Train an RF-DETR Model

  ---

  Learn how to train an RF-DETR model with the rfdetr Python package.

  Tutorial

• Deploy an RF-DETR Model

  ---

  Learn how to deploy an RF-DETR model in the cloud and on your device.

  Tutorial