YOLO12 introduces an attention-centric architecture that departs from the traditional CNN-based approaches used in previous YOLO models, yet retains the real-time inference speed essential for many applications. This model achieves state-of-the-art object detection accuracy through novel methodological innovations in attention mechanisms and overall network architecture, while maintaining real-time performance.
- **Area Attention Mechanism**: A new self-attention approach that processes large receptive fields efficiently. It divides [feature maps](https://www.ultralytics.com/glossary/feature-maps) into _l_ equal-sized regions (defaulting to 4), either horizontally or vertically, avoiding complex operations and maintaining a large effective receptive field. This significantly reduces computational cost compared to standard self-attention.
@ -31,32 +33,27 @@ YOLO12 introduces an attention-centric architecture that departs from the tradit
YOLO12 supports a variety of computer vision tasks. The table below shows task support and the operational modes (Inference, Validation, Training, and Export) enabled for each:
| Model Type | Task | Inference | Validation | Training | Export |
YOLO12 demonstrates significant [accuracy](https://www.ultralytics.com/glossary/accuracy) improvements across all model scales, with some trade-offs in speed compared to the _fastest_ prior YOLO models. Below are quantitative results for [object detection](https://www.ultralytics.com/glossary/object-detection) on the COCO validation dataset:
- Inference speed measured on an NVIDIA T4 GPU with TensorRT FP16 [precision](https://www.ultralytics.com/glossary/precision).
- Comparisons show the relative improvement in mAP and the percentage change in speed (positive indicates faster; negative indicates slower). Comparisons are made against published results for YOLOv10, YOLO11, and RT-DETR where available.
Glenn Jocher
3 weeks ago
committed by
GitHub