YOLOv4: Optimal Speed and Accuracy of Object Detection

May 2020

tl;dr: The ultimate guide to train a fast and accurate detector with limited resource.

Overall impression

The paper has a very nice review of object detection, including one-stage object detectors, two-stage object detectors, anchor-based ones and anchor-free ones.

Yolov4 is highly practical and focuses on training fast object detectors with only one 1080Ti or 2080Ti GPU card. Yolov4 runs twice as fast as EfficientDet.

Overall YOLOv4 is not very friendly to be deployed, given the darknet framework. Two better and more industry-friendly solutions are:

Key ideas

Technical details