arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.14239cs.CV
收藏

LeYOLO:用于目标检测的新型嵌入式架构

LeYOLO, New Embedded Architecture for Object Detection

Université de Reims Champagne-Ardenne(雷姆斯香槟-阿登大学);CEA(法国原子能委员会);LRC DIGIT(DIGIT实验室);LICIIS;INRAE(法国国家农业食品与环境研究委员会);RIBP USC 1488

Lilian Hollard, Lucas Mohimont, Nathalie Gaveau, Luiz Angelo Steffenel

AI总结:

本文提出LeNeck框架与LeYOLO轻量目标检测模型,以MSCOCO验证其在低参数量、低FLOP下兼顾高精度与速度,适用于移动、嵌入式及微控制器设备。

摘要:

深度神经网络中的高效计算对于实时目标检测至关重要。然而,近期进展主要来自高性能硬件的提升,而非参数和FLOP效率的改善。这一点在最新的YOLO架构中尤为明显,其速度被置于轻量化设计之上。因此,针对微控制器等低资源环境优化的目标检测模型受到的关注较少。对于计算能力有限的设备,现有解决方案主要依赖SSDLite或低参数分类器的组合,从而在类YOLO架构与真正高效的轻量级检测器之间形成明显差距。这引出一个关键问题:一个针对参数和FLOP效率优化的模型,能否达到与主流YOLO模型相当的精度水平?为解决该问题,我们以MSCOCO作为基础验证集,为目标检测模型提出两项关键贡献。第一,我们提出LeNeck,这是一个通用检测框架,可保持与SSDLite相当的推理速度,同时显著提高精度并减少参数量。第二,我们提出LeYOLO,这是一个高效目标检测模型,旨在提升基于YOLO架构的计算效率。LeYOLO有效弥合了基于SSDLite的检测器与YOLO模型之间的差距,在如同MobileNets一样紧凑的模型中提供高精度。这两项贡献尤其适用于移动设备、嵌入式设备和包括微控制器在内的超低功耗设备,在这些场景中计算效率至关重要。

英文摘要:

Efficient computation in deep neural networks is crucial for real-time object detection. However, recent advancements primarily result from improved high-performing hardware rather than improving parameters and FLOP efficiency. This is especially evident in the latest YOLO architectures, where speed is prioritized over lightweight design. As a result, object detection models optimized for low-resource environments like microcontrollers have received less attention. For devices with limited computing power, existing solutions primarily rely on SSDLite or combinations of low-parameter classifiers, creating a noticeable gap between YOLO-like architectures and truly efficient lightweight detectors. This raises a key question: Can a model optimized for parameter and FLOP efficiency achieve accuracy levels comparable to mainstream YOLO models? To address this, we introduce two key contributions to object detection models using MSCOCO as a base validation set. First, we propose LeNeck, a general-purpose detection framework that maintains inference speed comparable to SSDLite while significantly improving accuracy and reducing parameter count. Second, we present LeYOLO, an efficient object detection model designed to enhance computational efficiency in YOLO-based architectures. LeYOLO effectively bridges the gap between SSDLite-based detectors and YOLO models, offering high accuracy in a model as compact as MobileNets. Both contributions are particularly well-suited for mobile, embedded, and ultra-low-power devices, including microcontrollers, where computational efficiency is critical.

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。

↑