This paper presents a method for optimizing object detection models by combining weight pruning and singular value decomposition (SVD). The proposed method was evaluated on a custom dataset of street work images obtained from https://universe.roboflow.com/roboflow-100/street-work. The dataset consists of 611 training images, 175 validation images, and 87 test images with 7 classes. We compared the performance of the optimized models with the original unoptimized model in terms of frame rate, mean average precision (mAP@50), and weight size. The results show that the weight pruning + SVD model achieved a 0.724 mAP@50 with a frame rate of 1.48 FPS and a weight size of 12.1 MB, outperforming the original model (0.717 mAP@50, 1.50 FPS, and 12.3 MB). Precision-recall curves were also plotted for all models. Our work demonstrates that the proposed method can effectively optimize object detection models while balancing accuracy, speed, and model size.

翻译：本文提出了一种结合权重剪枝与奇异值分解（SVD）的目标检测模型优化方法。该方法在从 https://universe.roboflow.com/roboflow-100/street-work 获取的街道施工图像私有数据集上进行了评估。数据集包含611张训练图像、175张验证图像与87张测试图像，共涵盖7个类别。我们从帧率、平均精度均值（mAP@50）及权重文件大小三个维度，将优化后模型与原始未优化模型进行了性能对比。实验结果表明，权重剪枝+SVD模型实现了0.724的mAP@50，帧率达1.48 FPS，权重文件大小为12.1 MB，优于原始模型（mAP@50为0.717、帧率1.50 FPS、权重大小12.3 MB）。同时绘制了所有模型的精确率-召回率曲线。本研究证明，所提方法能在平衡精度、速度与模型大小的前提下有效优化目标检测模型。