arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08430cs.CV
收藏

YOLOX:2021年超越YOLO系列

YOLOX: Exceeding YOLO Series in 2021

Megvii Technology(旷视科技)

Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, Jian Sun

摘要:

本文介绍了对YOLO系列探测器的一些改进,形成了一种新的高性能探测器-- YOLOX。我们将YOLO探测器切换到无锚方式,并进行其他先进的探测技术,即,解耦头和领先的标签分配策略SimOTA在大规模模型范围内实现了最先进的结果:对于只有0.91 M参数和1.08 G FLOP的YOLO-Nano,我们在COCO上获得了25.3%的AP,超过NanoDet 1.8%的AP;对于YOLOv 3,行业中使用最广泛的探测器之一,我们在COCO上将其提升到47.3%AP,比当前最佳实践高出3.0%AP;对于与YOLOv 4-CSP、YOLOv 5-L具有大致相同数量的参数的YOLOX-L,我们在COCO上以68.9 FPS的速度在Tesla V100上实现50.0% AP,超过YOLOv 5-L 1.8% AP。此外,我们使用一个YOLOX-L模型赢得了流感知挑战赛(CVPR 2021自动驾驶研讨会)的第一名。我们希望这份报告能为实际场景中的开发者和研究者提供有用的经验,同时我们也提供了支持ONNX、TensorRT、NCNN和Openvino的部署版本。源代码位于https://github.com/Megvii-BaseDetection/YOLOX。

英文摘要:

In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX. We switch the YOLO detector to an anchor-free manner and conduct other advanced detection techniques, i.e., a decoupled head and the leading label assignment strategy SimOTA to achieve state-of-the-art results across a large scale range of models: For YOLO-Nano with only 0.91M parameters and 1.08G FLOPs, we get 25.3% AP on COCO, surpassing NanoDet by 1.8% AP; for YOLOv3, one of the most widely used detectors in industry, we boost it to 47.3% AP on COCO, outperforming the current best practice by 3.0% AP; for YOLOX-L with roughly the same amount of parameters as YOLOv4-CSP, YOLOv5-L, we achieve 50.0% AP on COCO at a speed of 68.9 FPS on Tesla V100, exceeding YOLOv5-L by 1.8% AP. Further, we won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021) using a single YOLOX-L model. We hope this report can provide useful experience for developers and researchers in practical scenes, and we also provide deploy versions with ONNX, TensorRT, NCNN, and Openvino supported. Source code is at https://github.com/Megvii-BaseDetection/YOLOX.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑