YOLOV6: A SINGLE-STAGE OBJECT DETECTION FRAMEWORK FOR INDUSTRIAL APPLICATIONS

Chuyi Li, Bo Zhang, Lulu Li, Liang Li, Yifei Geng, Meng Cheng, Xu Xiaoming, Xiangxiang Chu, Xiaoming Wei

Keywords: object detection, single-stage

TL;DR: An industrial-tailored single-stage object detector

Abstract: We inaugurate YOLOv6, shipped with hardware-friendly architectural designs and a composite of novel training schemes tailored for industrial scenarios, which marks a new state-of-the-art real-time object detector as of early 2023. For a glimpse of performance, our YOLOv6-N hits 37.5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 45.0% AP at 484 FPS, outperforming other mainstream detectors at the same scale (YOLOv5-S, YOLOv8-S, YOLOX-S, and PPYOLOE-S). Meantime, YOLOv6-M and L achieve better accuracy performance (50.0%/52.8% respectively) than other detectors at a similar inference speed. Additionally, with an extended backbone and neck design, our YOLOv6-L6 achieves state-of-the-art accuracy in real-time object detection. We carefully conducted extensive experiments to validate the effectiveness of each proposed component.

Primary Area: general machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2412