用教师模型蒸馏出轻量学生模型，高效识别停车位
Optimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers
- 用多个教师模型生成伪标签，训练轻量化学生模型
- 学生模型参数少26倍，准确率达96.6%，高于教师模型的95.3%
- 适合边缘设备部署，降低城市智能监控数据传输压力
在智慧城市建设中，基于图像的停车空间监测需将大量数据上传至中心服务器进行分类，对网络和硬件基础设施要求高。为解决此问题，本文提出构建一个稳健的分类器集成作为教师模型，并将其知识蒸馏到轻量级专用学生模型中，可在边缘设备直接部署。通过教师模型生成伪标签样本，在目标场景上微调学生模型。实验显示，学生模型参数量仅为教师模型的1/26，但在目标测试集上平均准确率达96.6%，超过教师模型的95.3%。
原文摘要 · Abstract (English)
When deploying large-scale machine learning models for smart city applications, such as image-based parking lot monitoring, data often must be sent to a central server to perform classification tasks. This is challenging for the city's infrastructure, where image-based applications require transmitting large volumes of data, necessitating complex network and hardware infrastructures to process the data. To address this issue in image-based parking space classification, we propose creating a robust ensemble of classifiers to serve as Teacher models. These Teacher models are distilled into lightweight and specialized Student models that can be deployed directly on edge devices. The knowledge is distilled to the Student models through pseudo-labeled samples generated by the Teacher model, which are utilized to fine-tune the Student models on the target scenario. Our results show that the Student models, with 26 times fewer parameters than the Teacher models, achieved an average accuracy of 96.6% on the target test datasets, surpassing the Teacher models, which attained an average accuracy of 95.3%.
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。