#52 · Primary category： Computer Vision
rf-detr
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
Project last updated：08/25/26
GitHub Stars
9.1K
Forks
1.1K
Contributors
95
License
Apache-2.0
Why we included this project
RF-DETR pairs a DINOv2 backbone with a real-time transformer head, so one model handles object detection, instance segmentation, and keypoint detection through the same API. Roboflow built it to be fine-tuned rather than used out of the box, and the accuracy-versus-latency results on COCO make it a practical alternative to the older YOLO-style detectors. The Apache-2.0 weights and the rfdetr package let you retrain on your own data, whether that means counting parts on a production line or finding objects in satellite and medical imagery. Fine-tuning notebooks and a Hugging Face demo lower the barrier for teams who have not worked with DETR-style architectures before. If your stack is built around vision rather than LLMs, this one is worth a closer look.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)