detrex 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 detrex among their alternatives. The relationship is not symmetric — how detrex rates them is a separate judgement, made when detrex is analysed in its own right.
calls detrex “choose if you prefer DETR-style transformer detection over YOLO.”
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
calls detrex “DETR-focused detection platform, choose for transformer-based research.”
OpenMMLab Detection Toolbox and Benchmark
calls detrex “PyTorch DETR-centric research platform — choose if you need DETR-family models in PyTorch, not the breadth of PaddleDetection.”
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
calls detrex “choose it when you are doing research on DETR-style detection and need a modular platform for building/benchmarking variants.”
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 detrex “Use it as a DETR research platform to train custom transformer detectors, accepting a less turnkey pipeline.”
[CVPR 2024] Real-Time Open-Vocabulary Object Detection