DETRs Beat YOLOs on Real-time Object Detection

🤖 Plain-English Summary

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. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% 156.2% AP.

🔑 Key Findings

• 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.

🔗 Related Resources