👁️

Object Detection - RF-DETR Medium

🛠

Find Objects in a Photo, Fast

A modern object detector from Roboflow. Point it at any photo, and it draws boxes around the things it finds - people, cars, dogs, chairs, food, and 76 other everyday categories - with a confidence score for each one. The "Medium" version is the all-around pick: meaningfully more accurate than tiny detectors, much faster than the largest ones.

What it does

RF-DETR-Medium looks at a photo and tells you what's in it and where each thing is. For every object it spots, it returns three pieces of information: a label ("person", "car", "dog"), a box drawn around the object, and a confidence score from 0 to 1 saying how sure it is. It's been trained to recognize 80 everyday categories from the well-known COCO dataset - people, animals, vehicles, household items, food, sports equipment, and more. The model is part of Roboflow's RF-DETR family, a new generation of object detectors built to be both accurate and fast enough for real-time use. The "Medium" size is the balanced choice for most projects: more accurate than the small variants, faster than the large ones.

Problem it solves

  • Find lots of things at once - Detect and locate multiple objects in a single photo in one shot (no need to scan the image piece-by-piece)
  • Real-time-friendly - Designed for fast inference, so it works for live video, surveillance, robotics, or any setting where speed matters
  • Modern, accurate detector - Uses a newer transformer-based design that's typically more accurate than older detectors of the same size
  • 80 everyday categories out of the box - People, vehicles, animals, furniture, food, sports gear, electronics, and more - covers most common scenes
  • Great starting point for custom training - Roboflow released this family specifically so teams can fine-tune it on their own object categories
  • Easy to plug in - Works directly with the popular Hugging Face Transformers library, so it slots into existing pipelines with minimal effort

Input/Output

  • Input: A regular color photo (PNG, JPEG, etc.)
    • image
  • Options:
    • Minimum confidence score to keep a detection (0.0 – 1.0, default 0.5)
      • Only detections with a confidence score at or above this threshold are returned
      • Higher = fewer, more confident boxes; lower = more boxes, including weaker guesses
  • Output: A list of detected objects. For each one:
    • Label – What it is (e.g., "person", "car", "dog", "chair")
    • Box – Where it is in the image, given as [left, top, right, bottom] pixel coordinates
    • Confidence – How sure the model is, from 0.0 to 1.0
      • A confidence threshold of ~0.35 – 0.5 is a sensible cutoff for keeping detections in most use cases
        • image
        image

Accuracy

Model size
33.7 million parameters — a mid-size model
Speed
Real-time on modern GPUs; the "Medium" pick on the speed-vs-accuracy spectrum
Where it sits in the family
RF-DETR comes in multiple sizes — Medium is the balanced default. Smaller variants are faster but less accurate; larger ones are more accurate but slower
How it compares to YOLO
At the same speed bracket, RF-DETR-Medium is more accurate than similarly fast YOLO detectors (e.g., +1.6 mAP over YOLO26m at slightly faster speed). The trade-off: RF-DETR uses more parameters, so it needs more memory than YOLO of the same "size letter"
What it recognizes
80 everyday object categories (the standard COCO list)
How it detects
One pass over the image — no need for older multi-step detection tricks
Good for
Production object detection where accuracy matters and you want better results than YOLO at similar speed

Technical Details

Architecture
RF-DETR — DINOv2-with-registers ViT backbone + multi-scale projector + Deformable DETR decoder
Backbone Detail
DINOv2-with-registers style ViT with RF-DETR's windowed / full attention alternation for efficient self-attention
Multi-scale Fusion
RF-DETR multi-scale projector (C2f-style blocks in the LW-DETR lineage) aggregates multi-level backbone features before the decoder
Decoder
Deformable DETR-style decoder with multi-scale deformable cross-attention
Object Queries
DETR-style queries with bipartite matching and auxiliary decoder losses for training stability
Training Losses
Classification + bounding-box L1 + GIoU, with auxiliary supervision on intermediate decoder layers
Training Tricks
Group DETR (parallel decoder copies during training for faster convergence)
Family Discovery
Weight-sharing Neural Architecture Search (NAS) over practical accuracy/latency knobs — Medium is one subnet on the frontier
Parameters
33.7M (F32 weights)
Training Data
COCO 2017 (80 categories, as reflected in config.id2label)
Supported Frameworks
Hugging Face Transformers (RfDetrForObjectDetection), Safetensors
Paper
"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers" — arXiv:2511.09554 (Robinson et al., Nov 2025)

Compliance & Provenance

Provider
Roboflow (open)
Provider type
Specialized
License
Apache 2.0
EU AI Act risk class
Minimal Risk
Art. 50 transparency
Not applicable
Region availability
Available globally
Training data summary
Provider model card / training data

For more on how we classify models and mark outputs, see our AI Policy.

Model Source