detr is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named detr among their alternatives. The relationship is not symmetric — how detr rates them is a separate judgement, made when detr is analysed in its own right.
calls detr “Choose for the original transformer end-to-end DETR baseline (Apache-2.0) if you accept an archived repo, not YOLOv7 real-time speed.”
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
calls detr “Choose it if you prefer a transformer-based end-to-end detector without hand-crafted components.”
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
calls detr “Choose when you want transformer-based end-to-end detection with no anchors or NMS; code is Apache-2.0 but unmaintained/archived.”
Object detection, 3D detection, and pose estimation using center point detection:
calls detr “choose it only as the original DETR reference for research/education; it is old, unmaintained, and not real-time.”
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
calls detr “Only for reproducing end-to-end DETR research; archived, slow to converge, and fixed-class.”
[CVPR 2024] Real-Time Open-Vocabulary Object Detection