R

Rtdetr R50vd Coco O365

Developed by PekingU
RT-DETR is the first real-time end-to-end object detector, achieving 53.1% AP and 108 FPS on the COCO dataset through an efficient hybrid encoder and uncertainty-minimized query selection mechanism.
Downloads 111.17k
Release Time : 5/21/2024

Model Overview

Real-Time Detection Transformer (RT-DETR) is an end-to-end object detector that eliminates the need for Non-Maximum Suppression (NMS), achieving high-speed and high-precision detection through improved encoders and query selection mechanisms.

Model Features

Efficient Hybrid Encoder
Rapidly processes multi-scale features by decoupling intra-scale interaction and cross-scale fusion
Uncertainty-minimized Query Selection
Provides high-quality initial queries for the decoder to enhance detection accuracy
Flexible Speed Adjustment
Allows speed adjustment by modifying decoder layers without retraining
NMS-free Design
End-to-end architecture eliminates the Non-Maximum Suppression step in traditional object detection

Model Capabilities

Real-time Object Detection
Multi-scale Feature Processing
End-to-end Detection
High-precision Object Recognition

Use Cases

Intelligent Surveillance
Airport Security Check
Real-time detection of hazardous items in luggage
Maintains high detection accuracy in complex scenarios
Autonomous Driving
Road Object Detection
Real-time identification of vehicles, pedestrians, and other road participants
108 FPS processing speed meets real-time requirements
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase