加速非极大值抑制:一种图论视角
Accelerating Non-Maximum Suppression: A Graph Theory Perspective
AI总结:
本文首次从图论视角分析非极大值抑制,提出QSI-NMS和BOE-NMS两种加速方法,并构建首个NMS基准NMS-Bench,在几乎不损失mAP的情况下显著提升检测效率。
摘要:
非极大值抑制(NMS)是目标检测中不可或缺的后处理步骤。随着网络模型的持续优化,NMS已成为提升目标检测效率的“最后一公里”。本文首次从图论视角系统分析NMS,揭示其内在结构。据此,我们提出两种优化方法,即QSI-NMS和BOE-NMS。前者是一种快速的递归分治算法,mAP损失可忽略不计,其扩展版本(eQSI-NMS)实现了$\mathcal{O}(n\log n)$的最优复杂度。后者聚焦于NMS的局部性,在不损失mAP的前提下实现了常数级别的优化。此外,为便于研究人员快速评估NMS方法,我们引入了NMS-Bench,这是首个旨在全面评估各种NMS方法的基准。以MS COCO 2017上的YOLOv8-N模型作为基准设置,我们的方法QSI-NMS在该基准上提供了原始NMS的$6.2\times$速度,mAP下降$0.1\\%$。最优的eQSI-NMS仅下降$0.3\\%$ mAP,实现了$10.7\times$速度。同时,BOE-NMS在mAP无损失的情况下展现出$5.1\times$速度。
英文摘要:
Non-maximum suppression (NMS) is an indispensable post-processing step in object detection. With the continuous optimization of network models, NMS has become the ``last mile'' to enhance the efficiency of object detection. This paper systematically analyzes NMS from a graph theory perspective for the first time, revealing its intrinsic structure. Consequently, we propose two optimization methods, namely QSI-NMS and BOE-NMS. The former is a fast recursive divide-and-conquer algorithm with negligible mAP loss, and its extended version (eQSI-NMS) achieves optimal complexity of $\mathcal{O}(n\log n)$. The latter, concentrating on the locality of NMS, achieves an optimization at a constant level without an mAP loss penalty. Moreover, to facilitate rapid evaluation of NMS methods for researchers, we introduce NMS-Bench, the first benchmark designed to comprehensively assess various NMS methods. Taking the YOLOv8-N model on MS COCO 2017 as the benchmark setup, our method QSI-NMS provides $6.2\times$ speed of original NMS on the benchmark, with a $0.1\%$ decrease in mAP. The optimal eQSI-NMS, with only a $0.3\%$ mAP decrease, achieves $10.7\times$ speed. Meanwhile, BOE-NMS exhibits $5.1\times$ speed with no compromise in mAP.
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。