Post
1534
π Transformers are not here to take part but take over... and down goes real-time object detection! π₯
Enter Real-time DEtection Transformer (RT-DETR) π¦Ύ as suggested capable of real-time object detection. π―
Object DEtection Transformer (DETR) is not new ( @Meta did it eons ago) but it had the issue of every other transformer, high computational cost πΈ
RT-DETR brings an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed ποΈ
Gist is RT-DETR speeds up object detection by redesigning its encoder to process features more efficiently and selecting higher quality initial object queries. β‘
It also allows adjusting the number of decoder layers to balance speed and accuracy for different real-time scenarios. βοΈ
This makes RT-DETR faster and more accurate than previous YOLO models. π
How much betterπ/faster? β±οΈ
RT-DETR-R50 achieved 53.1% AP on COCO and 108 FPS on a T4 GPU, while RT-DETR-R101 achieved 54.3% AP and 74 FPS, outperforming advanced YOLO models in both speed and accuracy. πβ¨
π Paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
π§ Models: https://huggingface.co/models?search=pekingu/rt-detr
Enter Real-time DEtection Transformer (RT-DETR) π¦Ύ as suggested capable of real-time object detection. π―
Object DEtection Transformer (DETR) is not new ( @Meta did it eons ago) but it had the issue of every other transformer, high computational cost πΈ
RT-DETR brings an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed ποΈ
Gist is RT-DETR speeds up object detection by redesigning its encoder to process features more efficiently and selecting higher quality initial object queries. β‘
It also allows adjusting the number of decoder layers to balance speed and accuracy for different real-time scenarios. βοΈ
This makes RT-DETR faster and more accurate than previous YOLO models. π
How much betterπ/faster? β±οΈ
RT-DETR-R50 achieved 53.1% AP on COCO and 108 FPS on a T4 GPU, while RT-DETR-R101 achieved 54.3% AP and 74 FPS, outperforming advanced YOLO models in both speed and accuracy. πβ¨
π Paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
π§ Models: https://huggingface.co/models?search=pekingu/rt-detr