Breaking Down YOLO’s (version 4) State-Of-The-Art Performance

Author(s): Adrienne Kline

Originally published on Towards AI.

Coined after the viral phrase, ‘you only live once’ (YOLO), the machine learning (ML) world first coined this acronym and repurposed it to You Only Look Once — YOLO. YOLOv1 was devised as a deep learning architecture optimized for fast object detection. The latest installment of the YOLO architecture (YOLOv4) made its debut in April 2020 as the most recent iteration [1]. It was created by developers Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. YOLOv4 comes with superior computational speed and increased precision relative to its v3 counterpart.

With its increased speed, YOLOv4 is well suited to near real-time object… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI