DETRs Beat YOLOs on Real-time Object Detection

By Wenyu Lv, Shangliang Xu, Yian Zhao, Guanzhong Wang, Jinman Wei, Cheng Cui, Yuning Du, Qingqing Dang, Yi Liu. Computer Vision and Pattern Recognition, 2023

3,776 citations recorded by the source corpus.

The YOLO series has become the most popular frame-work for real-time object detection due to its reasonable trade-off between speed and accuracy. However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy. Specifically, we design an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed. Then, we propose the uncertainty-minimal query selection to provide high-quality initial queries to the decoder, thereby improving accuracy. In addition, RT-DETR supports flexible speed tuning by adjusting the number of decoder layers to adapt to various scenarios without retraining. Our RT-DETR-R50 /R101 achieves 53.1% 154.3% AP on COCO and 108 /74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% 156.2% AP. The project page: https://zhao-yian.github.io/RTDEtr.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3a6c423cc0f687fc43a671e55dce06f681df7476

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hongpeng Liao
2. Chien-Yao Wang
3. I-Hau Yeh
4. Kai Han
5. Yunhe Wang
6. Zijia Lin
7. Guiguang Ding
8. Jianyuan Guo

Citations in the corpus

• YOLOv10: Real-Time End-to-End Object Detection (2024, methodology): “Moreover, we follow [78] to establish the end-to-end speed benchmark.”
• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information (2024, methodology): “As for the amount of computation, the best existing models from the smallest to the largest are YOLO MS [7], PP YOLOE [74], and RT DETR [43].”
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception (2025, neutral): “Recent years have witnessed the dominance of single-stage CNN detectors that integrate region proposal, classification, and regression into a unified end-to-end framework in this field [4]–[7].”
• Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism (2023, methodology): “The recent RT-DETR [23] improved the encoder-decoder structure to solve the slow DETR-like model problem, outperforming YOLO-L/X in both accuracy and speed.”
• YOLOv12: Attention-Centric Real-Time Object Detectors (2025, neutral): “Compared to the end-to-end detectors RT-DETR-R18 [66] / RT-DETRv2-R18 [41], YOLOv12-S achieves beatable performance but with much better inference speed and less computational cost and fewer parameters.”