real-time object detection
YOLOv10 is a real-time end-to-end object detection model from THU-MIG, implementing a single-stage anchor-free detector.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Use it if you work in PaddlePaddle instead of PyTorch; offers the same YOLO architectures in a different framework.
🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, RT-DETR, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv10, YOLO11, YOLOX, YOLOv5u, YOLOv7u, YOLOv6Lite, RTMDet and so on. 🚀🚀🚀
Choose it if you need open-vocabulary detection with text prompts beyond fixed classes.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Use it for a broader, actively-maintained YOLO ecosystem with multiple models and task support.
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
Use it if you prefer PaddlePaddle and need a comprehensive detection toolbox with many architectures.
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Use it if you need a modular, versatile detection toolbox with many state-of-the-art architectures.
OpenMMLab Detection Toolbox and Benchmark
Choose it if you prefer a transformer-based end-to-end detector without hand-crafted components.
End-to-End Object Detection with Transformers
Choose it if you need a keypoint-based center detection alternative with simple post-processing.
Object detection, 3D detection, and pose estimation using center point detection:
Choose it if you want a transformer-based real-time detector with strong fine-tuning performance and commercial-friendly license.
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose it if you need a mature, industrial-focused YOLO variant with a simpler deployment footprint.
YOLOv6: a single-stage object detection framework dedicated to industrial applications.
Choose it if you require a lightweight, well-documented YOLO version for legacy or edge deployments.
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
Choose it if you need a reliable, widely-used YOLO version with extensive community support and export options.
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
These projects were analysed and named yolov10 among their alternatives. The relationship is not symmetric — how yolov10 rates them is a separate judgement, made when yolov10 is analysed in its own right.
calls yolov10 “Choose it for NMS-free real-time latency on fixed classes, without open-vocabulary prompting.”
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
calls yolov10 “choose if you specifically want YOLOv10's end-to-end detection, but you lose the multi-task API of Ultralytics.”
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking