轻量级模型在微控制器上实现高精度，兼顾速度与内存占用。
STResNet & STYOLO : A New Family of Compact Classification and Object Detection Models for MCUs
- 提出STResNet和STYOLO系列模型，专为资源受限设备优化。
- STResNetMilli仅300万参数达70.0%图像分类准确率，优于MobileNetV1。
- STYOLOMicro/Milli在COCO数据集上分别达30.5%/33.6%精度，超越YOLOv5n。
轻量级神经网络的进展显著提升了深度学习模型在边缘硬件上的部署效率。然而，现有多数架构仍以牺牲准确性换取延迟，限制了其在微控制器和神经处理器设备上的应用。本文提出两个新模型家族：用于图像分类的STResNet和用于目标检测的STYOLO，共同优化准确性、效率和内存占用。所提STResNet系列（从Nano到Tiny）在四百万参数预算内实现具有竞争力的ImageNet 1K准确率。其中，STResNetMilli仅用三百万参数即达到70.0%的Top 1准确率，在计算复杂度相当的情况下优于MobileNetV1和ShuffleNetV2。对于目标检测，STYOLOMicro和STYOLOMilli在MS COCO数据集上分别取得30.5%和33.6%的平均精度，同时在准确性和效率上超过YOLOv5n和YOLOX Nano。此外，当使用Ultralytics训练环境时，以STResNetMilli作为骨干网络表现优异。
原文摘要 · Abstract (English)
Recent advancements in lightweight neural networks have significantly improved the efficiency of deploying deep learning models on edge hardware. However, most existing architectures still trade accuracy for latency, which limits their applicability on microcontroller and neural processing unit based devices. In this work, we introduce two new model families, STResNet for image classification and STYOLO for object detection, jointly optimized for accuracy, efficiency, and memory footprint on resource constrained platforms. The proposed STResNet series, ranging from Nano to Tiny variants, achieves competitive ImageNet 1K accuracy within a four million parameter budget. Specifically, STResNetMilli attains 70.0 percent Top 1 accuracy with only three million parameters, outperforming MobileNetV1 and ShuffleNetV2 at comparable computational complexity. For object detection, STYOLOMicro and STYOLOMilli achieve 30.5 percent and 33.6 percent mean average precision, respectively, on the MS COCO dataset, surpassing YOLOv5n and YOLOX Nano in both accuracy and efficiency. Furthermore, when STResNetMilli is used as a backbone with the Ultralytics training environment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。