Real-time DEtection Transformer (RT-DETR) landed in @huggingface transformers 🤩 with Apache 2.0 license 😍  
Do DETRs Beat YOLOs on Real-time Object Detection? keep reading 👀  

![video_1](video_1.mp4)

Short answer, it does!  
📖 [notebook](https://t.co/NNRpG9cAEa), 🔖 [models](https://t.co/ctwWQqNcEt), 🔖 [demo](https://t.co/VrmDDDjoNw)

YOLO models are known to be super fast for real-time computer vision, but they have a downside with being volatile to NMS 🥲  
Transformer-based models on the other hand are computationally not as efficient 🥲 Isn't there something in between? Enter RT-DETR!  

The authors combined CNN backbone, multi-stage hybrid decoder (combining convs and attn) with a transformer decoder ⇓  

![image_1](image_1.jpg)

In the paper, authors also claim one can adjust speed by changing decoder layers without retraining altogether they also conduct many ablation studies and try different decoders (see below) 

![image_2](image_2.jpg)

The authors find out that the model performs better in terms of speed and accuracy compared to the previous state-of-the-art 🤩  

![image_3](image_3.jpg)

According to authors' findings, it performs way better than many of the existing models (including proprietary VLMs) and scales very well (on text decoder) 

> [!TIP]
Ressources:  
[DETRs Beat YOLOs on Real-time Object Detection](https://arxiv.org/abs/2304.08069) 
by Yian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei, Guanzhong Wang, Qingqing Dang, Yi Liu, Jie Chen (2023) 
[GitHub](https://github.com/lyuwenyu/RT-DETR/)  
[Hugging Face documentation](https://huggingface.co/docs/transformers/main/en/model_doc/rt_detr)  

> [!NOTE]
[Original tweet](https://twitter.com/mervenoyann/status/1807790959884665029) (July 1, 2024)