[CVPR2021/PaperSummary]YOLOX: Exceeding YOLO Series in 2021

Fig1:Speed-accuracy trade-off of accurate models (top) and Size-accuracy curve of lite models

1.Introduction

2. Proposed Architecture

Tab 1: Roadmap of YOLOX-Darknet53 in terms of AP (%) on COCO val.
Fig2: Training curves for detectors with YOLOv3 head or decoupled head. We
Tab 2: The effect of decoupled head for end-to-end YOLO in terms of AP (%) on COCO
Fig3: Illustration of the difference between YOLOv3 head and the proposed decoupled head
Eq1:SimOTA cost function
Table 3: Comparison of YOLOX and YOLOv5
Table 4: Comparison of YOLOX-Tiny and YOLOX-Nano
Table 5: Effects of data augmentation under different model sizes.

3. Comparison with the SOTA

Table 6: Comparison of the speed and accuracy of different object detectors on COCO 2017 test-dev

4. Conclusion

Writer’s Conclusion

References

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store