English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For years, the YOLO series has been the de facto industry-level standard forefficient object detection. The YOLO community has prospered overwhelmingly toenrich its use in a multitude of hardware platforms and abundant scenarios. Inthis technical report, we strive to push its limits to the next level, steppingforward with an unwavering mindset for industry application.  Considering the diverse requirements for speed and accuracy in the realenvironment, we extensively examine the up-to-date object detectionadvancements either from industry or academia. Specifically, we heavilyassimilate ideas from recent network design, training strategies, testingtechniques, quantization, and optimization methods. On top of this, weintegrate our thoughts and practice to build a suite of deployment-readynetworks at various scales to accommodate diversified use cases. With thegenerous permission of YOLO authors, we name it YOLOv6. We also express ourwarm welcome to users and contributors for further enhancement. For a glimpseof performance, our YOLOv6-N hits 35.9% AP on the COCO dataset at a throughputof 1234 FPS on an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 43.5% AP at 495 FPS,outperforming other mainstream detectors at the same scale~(YOLOv5-S, YOLOX-S,and PPYOLOE-S). Our quantized version of YOLOv6-S even brings a newstate-of-the-art 43.3% AP at 869 FPS. Furthermore, YOLOv6-M/L also achievesbetter accuracy performance (i.e., 49.5%/52.3%) than other detectors with asimilar inference speed. We carefully conducted experiments to validate theeffectiveness of each component. Our code is made available athttps://github.com/meituan/YOLOv6.

YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications